The daily ledger

ChatGPT Ads expands across Europe

ChatGPT Ads is expanding to 31 European markets. Learn how advertisers can reach people as they explore, compare options, and make decisions.

Mojo🔥 is now open source

Mojo🔥 is now open source Mojo🔥 is now open source The Mojo programming language has been promising an open source release since May 2023. Last week they shipped their 1.0 and today they have followed through on that…

Strengthening democratic oversight in national security

OpenAI launches an initiative to strengthen democratic oversight of AI in national security, supporting government institutions with tools, training, and expertise.

How Much Memory Does Your Agent Actually Need?

langchain-ai/langchain: langchain-openai==1.5.2

Changes since langchain-openai==1.5.1 release(openai): 1.5.2 (#39719) fix(openai): preserve reasoning item boundaries (#39278) release(openai): 1.5.2a1 (#39709) feat(openai): extract gateway metadata from response…

pytorch/pytorch: viable/strict/1787086487: Add missing XPU: _safe_softmax_xpu dispatch for _safe_softmax (#193786)

Descriptions: Root cause: Commit 08c29108 ("Remove the obsolete folder yaml/") in torch-xpu-ops migrated XPU dispatch registrations from torch-xpu-ops/yaml/native/native_functions.yaml to PyTorch's…

pytorch/pytorch: viable/strict/1787070441: Match Triton Python float signatures for user-defined kernels (#190340)

Fix Inductor wrapper codegen for user-defined Triton kernels so literal Python float launch arguments use Triton's normal fp32 signature behavior instead of being forced through Inductor's fp64 policy for Python floats.…

pytorch/pytorch: viable/strict/1787068774: [inductor] Preserve input placeholders during graph cleanup (#193708)

Issue Fixes #193705 Summary remove_redundant_views() (torch/_inductor/fx_passes/joint_graph.py) erases any zero-user node it's tracking, including graph placeholders — shrinking the compiled function's arity while the…

pytorch/pytorch: viable/strict/1787068166: Add IPC support for torch.xpu.Event (#192495)

Motivation As title Additional Context CI passed. Pull Request resolved: #192495 Approved by: https://github.com/gujinghui, https://github.com/albanD

Pacing model development in an era of cyber-critical capabilities

OpenAI is strengthening monitoring, alignment, and security for frontier AI models. See how new safeguards are guiding the pace of model development.

Introducing ChatGPT for Teens: Built for learning, backed by protections

ChatGPT for Teens helps teens learn, think critically, and use AI with confidence, with stronger built-in protections, healthy-use features, and additional controls for parents.

Partnering with CodeAI to prepare the first AI generation

OpenAI and CodeAI are partnering to help students build AI literacy, think critically about AI, and develop the skills to use and shape it responsibly.

pytorch/pytorch: trunk/755a76e8ca61827d785a7385eb5560a06f637a52

[Testcase Refactoring] Make test_cuda_event_eq device-agnostic via in…

pytorch/pytorch: viable/strict/1787058379

[Testcase Refactoring] Make test_cuda_event_eq device-agnostic via in…

Asana cleared 5 years of engineering work in 2 weeks with Codex

Asana used OpenAI Codex to replace an outdated testing system in two weeks, completing work expected to take five years for about $12K.

pytorch/pytorch: viable/strict/1787048801

[Inductor] Use schedule-first bounded regions for combo kernel memory…

pytorch/pytorch: trunk/547c669eac6b09aeef5a55ad175b1e451f07bbf6

[pt2] Fix barrier deps to exclude nodes defined after sync point (#19…

pytorch/pytorch: viable/strict/1787047062

[pt2] Fix barrier deps to exclude nodes defined after sync point (#19…

pytorch/pytorch: viable/strict/1787045245: Provide script to swap between upstream Triton and FBTriton (#193637)

Provide script to swap between upstream Triton and FBTriton for torchTLX dev works. python tools/torchtlx/dev.py doctor python tools/torchtlx/dev.py switch fbtriton --from-source /data/users/daohang/fbtriton python…

pytorch/pytorch: trunk/4863ab717405bf9de70625ca7622c28ad864a0ac: Provide script to swap between upstream Triton and FBTriton (#193637)

Provide script to swap between upstream Triton and FBTriton for torchTLX dev works. python tools/torchtlx/dev.py doctor python tools/torchtlx/dev.py switch fbtriton --from-source /data/users/daohang/fbtriton python…

pytorch/pytorch: viable/strict/1787041685

[c10][cuda] Per-stream expandable-segment reserve downsizing (#192269…

pytorch/pytorch: trunk/0a9cc3c7ada1690923a7ec9906c3a464db3a8621

[c10][cuda] Per-stream expandable-segment reserve downsizing (#192269…

pytorch/pytorch: viable/strict/1787038138

[qnnpack] Add 1..4x8 dynamic-quant aarch64 q8gemm microkernel for sma…

pytorch/pytorch: trunk/74db7b68313194366f2047f2c17bfc5e754bf50f

[qnnpack] Add 1..4x8 dynamic-quant aarch64 q8gemm microkernel for sma…

pytorch/pytorch: trunk/9ff255cb2d385bd7306ac815b0ba9def13213eb2

[TEST][CUDA] Bump reflection_pad_2d decomp test to use bfloat16 thr…

langchain-ai/langchain: langchain-openai==1.5.2a1

Initial release release(openai): 1.5.2a1 (#39709) feat(openai): extract gateway metadata from response headers when available (#39706) chore(openai): update snapshots (#39657) fix(openai): support o-series models in…

pytorch/pytorch: trunk/4e87387fdbb5d3c429210bd42fdc5903106d417c: Add TORCH_COMPILE_STATIC_SOURCES (#193626) (#193626)

Summary: Mirror TORCH_COMPILE_DYNAMIC_SOURCES, we add TORCH_COMPILE_STATIC_SOURCES (or torch.compiler.config.static_sources) to pass a list of source names that should be marked as static. This is useful when automatic…

pytorch/pytorch: trunk/81d0d1099cd05f16c8a030cd8a9c2d8fe283a5b2: [inductor] Fuse interleaved sub-parent reduction epilogues (#190594)

Teach SIMD scheduling and codegen to fuse reduction epilogues that consume interleaved pairs from a parent tile. This enables standalone NVFP4 packing while rejecting ambiguous, mutated, and non-leaf consumers.…

pytorch/pytorch: trunk/5a54183192278f3f9bbd8afdddb8f877c1af4112: Revert "[BE][Ez]: Update c10::complex kernels to use sincos (#193729)"

This reverts commit e734072. Reverted #193729 on behalf of https://github.com/jeanschmidt due to it have problems with CCCL 2.4.0 and older (comment)

pytorch/pytorch: viable/strict/1787032599: [Inductor][CUDA] Do not pad if using pointwise lowering (#192072)

Cases of test_small_mm_pointwise are failing flakily in test/inductor/test_mmdecomp.py on GB200 because the lowering pathway runs autotuning to determine whether to pad or not- this generally favors the pointwise…

pytorch/pytorch: trunk/6cfb8d6de6725c15b1b17a152282420e9af6c21a: [Inductor][CUDA] Do not pad if using pointwise lowering (#192072)

Cases of test_small_mm_pointwise are failing flakily in test/inductor/test_mmdecomp.py on GB200 because the lowering pathway runs autotuning to determine whether to pad or not- this generally favors the pointwise…

pytorch/pytorch: trunk/0d4c2dc53aa3396692f77e1c243f0bcb8452bcc7

[ATen][CPU] Speed up sort by packing (value, index) into a contiguous…

pytorch/pytorch: viable/strict/1787029120

[dynamo] Split FrozensetVariable off SetVariable to match CPython (#1…

pytorch/pytorch: trunk/59f3b801525091f62616f715c49846175c74272d

[dynamo] Split FrozensetVariable off SetVariable to match CPython (#1…

How NVIDIA scales expertise with ChatGPT Work

NVIDIA teams use ChatGPT Work to reduce manual tasks, connect fast-moving signals, and scale successful workflows globally.

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

We still don’t know how people are really using AI

AI companies like Anthropic and OpenAI regularly publish reports on how people are using products like Claude and ChatGPT, but they only release the data they want us to see, AI researchers say. “There is no independent…

AI’s recursive self-improvement might not come so quickly after all

The AI industry’s boldest promise right now is that AI will soon improve itself, with almost no need for human oversight. LLMs can already write code, generate synthetic data for training, and optimize the computer…

PERO: Efficient Robust Post-Training Foundation Models for Encrypted Traffic Classification

arXiv:2608.15504v1 Announce Type: new Abstract: Encrypted traffic classification is vital for network security, yet real-world deployments are inherently sensitive to rare but high-loss errors such as misclassification…

Advancing Open and Reproducible Relational Learning: RelArena-$\alpha$, TabPFN-Rel and RPI

arXiv:2608.16319v1 Announce Type: new Abstract: This first release of Prior Labs in relational learning shows our continued commitment to open science. We open-source three pieces of software that we expect to…

Koopman early warning signals for bifurcation and rate-induced tipping

arXiv:2608.14716v1 Announce Type: cross Abstract: Abrupt transitions in complex systems are often preceded by early warning signals. However, most indicators rely on the notion of critical slowing down and do not…

Beyond $L_2$: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architectures

arXiv:2608.16773v1 Announce Type: new Abstract: Prototype-based neural networks are hailed as interpretable-by-design architectures. Recently, Abductive Latent Explanations (ALE) were introduced to provide formal,…

PIKFNO: An Interpretable Neural Operator Based on Physics Informed Kernel Function

arXiv:2608.14619v1 Announce Type: new Abstract: This work proposes a new interpretable neural operator framework, termed the Physics Informed Kernel Function Neural Operator (PIKFNO), which explicitly incorporates…

Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays

arXiv:2608.14639v1 Announce Type: new Abstract: Per-field accept/review with selective risk at most alpha -- accept a field only if the error rate among accepted fields is controlled -- is the trust contract…

FedPA-LoRA: Product-Aligned Framework for Mitigating Aggregation and Initialization Errors in Heterogeneous Federated LoRA

arXiv:2608.15381v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables efficient federated fine-tuning of large language models, but its factorized parameterization creates a tension between accurate…

Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search

arXiv:2608.15669v1 Announce Type: new Abstract: Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein…

Represent, Then Generate: Multimodal-Conditioned Time-Series Generation under Irregular Missingness

arXiv:2608.12592v2 Announce Type: replace Abstract: Continuous physiological time series underpin modern clinical monitoring, yet many of the most informative signals are invasive, expensive, or simply unavailable for a…

Doubly robust nearest neighbors in factor models

arXiv:2211.14297v4 Announce Type: replace-cross Abstract: We introduce and analyze an improved variant of nearest neighbors (NN) for estimation with missing data in latent factor models. We consider a matrix completion…

Conditional Evaluation of Language Models with Cheap Auxiliary Signals

arXiv:2608.16210v1 Announce Type: new Abstract: Aggregate accuracy hides where models succeed and fail. Estimating conditional performance profiles from gold labels alone is expensive, while cheap auxiliary signals such…

Transfer Learning of Keystroke Dynamics for Cross-Device User Authentication

arXiv:2608.16334v1 Announce Type: new Abstract: Keystroke dynamics (typing patterns) can be used as a behavioural biometric modality for user authentication, with applications such as fraud prevention. While the…

Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation

arXiv:2608.14655v1 Announce Type: new Abstract: Omni-Large Language Models (Omni-LLMs) power complex multi-modal reasoning in applications like World Action Models and autonomous agents. However, their strong…

Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms

arXiv:2608.14653v1 Announce Type: new Abstract: Prediction uncertainty is a widely adopted metric for quantifying model confidence, with downstream applications spanning model explanation, data selection, and prediction…

LLM-based Framework for Generating and Verifying Parallel DEVS Statecharts

arXiv:2608.14956v1 Announce Type: new Abstract: The development of models demands sound modeling and simulation knowledge as well as domain knowledge. Every model should accurately represent a system's dynamics and be…

TransfHAR: Self-Supervised Wrist Representations for On-Demand Activity Recognition

arXiv:2608.15861v1 Announce Type: new Abstract: Fine-grained wrist activity recognition can support applications such as procedural step guidance and context-aware assistance, yet acquiring labeled data for every new…

TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH

arXiv:2608.16410v1 Announce Type: new Abstract: Combined algorithm selection and hyperparameter optimization (CASH) searches a conditional space in which the selected model determines which hyperparameters are active.…

CrevasseSeg: A Label-Efficient UAV Crevasse Segmentation Framework

arXiv:2608.15790v1 Announce Type: new Abstract: Crevasse mapping from uncrewed aerial vehicle (UAV) imagery matters for glaciological research and for field safety in glaciated terrain. Yet, pixel-level annotation of…

Retrieval-guided Twin Fusion with Similarity-aware Contrast for Molecule-Text Alignment

arXiv:2608.16005v1 Announce Type: new Abstract: This paper studies the problem of molecule-text alignment, which aims to project molecules and their textual descriptions into a joint latent space for downstream tasks…

Replacing Tunable Parameters in Weather and Climate Models with State-Dependent Functions using Reinforcement Learning

arXiv:2601.04268v4 Announce Type: replace Abstract: Weather and climate models rely on parametrisations to represent unresolved sub-grid processes. Traditional schemes rely on fixed coefficients that are weakly…

Whose Gold? Annotator-Pool Disagreement Is Large at the Item Level, and Hidden by Small Leaderboards

arXiv:2608.15980v1 Announce Type: cross Abstract: Preference benchmarks are built by hiring annotators, and the identity of those annotators is treated as an implementation detail. We measure what that detail buys. On…

NPU Offloading of a Frozen Visual Encoder for Robot Policy Training

arXiv:2608.15002v1 Announce Type: cross Abstract: When a robot policy is trained for a new task or dataset, its visual encoder can be frozen and only its action generation module trained, reducing training cost.…

Cross-Modal Ultrasound-MRI Learning for Fetal Brain Ventricular Volumetry and Abnormality Screening

arXiv:2608.14763v1 Announce Type: cross Abstract: Assessment of ventriculomegaly (VM) on fetal brain ultrasound relies primarily on measuring lateral ventricular atrial width on standard planes, which is…

One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail

arXiv:2608.14683v1 Announce Type: new Abstract: Given a patient's clinical findings, a diagnostic system ranks possible diseases and must decide when to endorse its first prediction or defer it for review. This decision…

Predicting, Evaluating, and Explaining Top Misinformation Spreaders via Archetypal User Behavior

arXiv:2608.16323v1 Announce Type: cross Abstract: The spread of misinformation on social networks poses a significant challenge to online communities and society at large. Not all users contribute equally to this…

A Counterexample to the Tang Zhang Schatten Norm Conjecture and Sharp Positive Results

arXiv:2608.15558v1 Announce Type: cross Abstract: For $m\geq 2$, let $c_p(m)$ be the all-dimensional best constant in $$ \left\|\sum_{k=1}^m A_k\right\|_p \leq c_p(m)\left\|\sum_{k=1}^m |A_k|\right\|_p. $$ Tang and…

MIRROR: Multimodal Intelligent Radiology Reasoning and Observation Reporter

arXiv:2608.16709v1 Announce Type: cross Abstract: A radiologist reading a model's output faces two problems. The model returns a number and no reason, and any system that turns that number into readable prose can…

Data-Driven Reconstruction of Spatially Resolved Electron and Ion Energy Distributions from Macroscopic Plasma Quantities with Deep Neural Networks

arXiv:2608.16519v1 Announce Type: cross Abstract: Spatially resolved EEDFs/IEDFs provide essential kinetic information about low-temperature plasmas (LTPs) and play a central role in determining transport, chemical…

AdROD: HyperNetwork-based Adversarially Robust Object Detection for Autonomous Driving

arXiv:2608.16031v1 Announce Type: new Abstract: Camera-based object detectors are vulnerable to physical adversarial attacks designed to suppress detections. While adversarial training and input purification offer some…

Dynamic Pricing and Advertising with Demand Learning

arXiv:2304.14385v4 Announce Type: replace-cross Abstract: We consider a novel pricing and advertising framework in which a seller not only sets the product price but also designs flexible advertising schemes to…

Look Before You Lift: Visual and Quantitative Diagnostics for Topological Deep Learning

arXiv:2608.15388v1 Announce Type: new Abstract: Topological deep learning (TDL) methods rely on lifting raw data into higher-order discrete domains such as simplicial complexes, cell complexes, and hypergraphs. In…

FDA-Opt: Federated Fine-Tuning via Dynamic Update Schedules

arXiv:2505.04535v4 Announce Type: replace Abstract: Federated Learning (FL) enables the utilization of vast, previously inaccessible data sources. At the same time, pre-trained Language Models (LMs) have taken the world…

Time-Correlated Video Bridge Matching

arXiv:2510.12453v3 Announce Type: replace Abstract: Diffusion models excel in noise-to-data generation tasks, providing a mapping from a Gaussian distribution to a more complex data distribution. However, they struggle…

M-LINKX: Multiview Graph Learning for Brain Cognitive Disease Detection

arXiv:2608.14847v1 Announce Type: new Abstract: Electroencephalogram (EEG) is a non-invasive and relatively low-cost procedure that measures brain electricity for the detection of cognitive diseases. EEG-based…

Knowing When to Defer: Selective Prediction for Responsible Knowledge Tracing

arXiv:2509.21514v4 Announce Type: replace Abstract: Research on Knowledge Tracing (KT) models traditionally focuses on improving predictive accuracy. However, responsible real-world deployment requires models to know…

When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation

arXiv:2608.15639v1 Announce Type: cross Abstract: \textit{Split Federated Learning} (SFL) enables distributed model training by splitting networks between the server and clients. However, under client heterogeneity, the…

SkillComposer: Learning Reusable Skills for Natural-Language Robot Programming

arXiv:2608.14944v1 Announce Type: cross Abstract: Natural-language interfaces can lower the barrier to programming robots, but existing systems struggle when users request complex tasks. While large language models…

Spectral Rank Certification for Foundation Model Adapters

arXiv:2608.15351v1 Announce Type: new Abstract: Nominal LoRA rank is a design parameter; calibrated spectral evidence is a separate inferential quantity. This article develops a finite-sample framework for inferring…

Hierarchical Copula-Gumbel-Top-K Routing: Two-Sided Dependence Control for Frozen Mixture-of-Experts at Fixed Per-Token Routing Laws

arXiv:2607.28670v3 Announce Type: replace Abstract: A stochastic Gumbel-Top-K router defines, for every token of a mixture-of-experts (MoE) model, a routing law: a distribution over ordered expert lists and mixture…

Detecting Money Laundering in Rwandan Mobile Money: A Machine Learning Framework

arXiv:2608.15447v1 Announce Type: new Abstract: Mobile money has widened financial access across Sub-Saharan Africa and enlarged the surface for money-laundering and terrorism-financing (ML/TF) activity in ecosystems…

UniFed-VLM: Federated Instruction Tuning for Vision-Language Models with Multiple Heterogeneity

arXiv:2608.15516v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated strong performance in multimodal understanding and generation. However, fine-tuning of VLMs typically relies on centralized…

L3Cube-IndicQuest v2: A Large-Scale Multilingual Benchmark for Evaluating Factual Knowledge of Large Language Models Across Indic Languages

arXiv:2608.15535v1 Announce Type: cross Abstract: We present L3Cube-IndicQuest v2, a large-scale gold-standard multilingual question-answering benchmark for evaluating the India-specific factual knowledge of Large…

Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts

arXiv:2608.15621v1 Announce Type: cross Abstract: Human Activity Recognition (HAR) with self-administered wearables, such as at-home rehabilitation and exercise monitoring, often requires reattaching inertial…

Solvable Sokoban Without a Solver via Diffusion

arXiv:2608.15958v1 Announce Type: cross Abstract: Deciding whether a Sokoban puzzle is solvable is PSPACE-complete (Culberson, 1997): solutions can be exponentially long and there is no short certificate to check.…

Reference-free logged energy-oracle recovery for neural approximations of symmetric coercive variational problems: conforming Riesz reconstruction and archive-level selection

arXiv:2608.16473v1 Announce Type: new Abstract: Neural PDE training yields a finite checkpoint archive, yet its logged energy errors are inaccessible without the exact solution, while loss-based selection does not…

Can Attribution Predict Risk? From Multi-View Attribution to Planning Risk Signals in End-to-End Autonomous Driving

arXiv:2605.06264v2 Announce Type: replace Abstract: End-to-end autonomous driving models generate future trajectories from multi-view inputs, improving system integration but introducing opaque decisions and…

UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures

arXiv:2608.16696v1 Announce Type: new Abstract: Physical AI systems such as autonomous vehicles and robots rely on timely exchange of high-dimensional sensory signals under tight bandwidth, latency, and energy budgets.…

Self-Supervised Auxiliary Task Discovery for Stable Reinforcement Learning in Stock Trading

arXiv:2608.15841v1 Announce Type: new Abstract: Reinforcement learning has gained increasing attention as a data-driven approach for stock trading. However, learning a policy that is both profitable and stable remains…

Diffusion-model approach to flavor models: A case study for $S_4^\prime$ modular flavor model

arXiv:2504.00944v2 Announce Type: replace-cross Abstract: We propose a numerical method of searching for parameters with experimental constraints in generic flavor models by utilizing diffusion models, which are…

FinFraudBench: A Heterogeneous Graph Benchmark for Financial Fraud Detection

arXiv:2608.15177v1 Announce Type: new Abstract: The increasing complexity of digital financial systems has reshaped financial fraud detection from isolated transaction classification into relational risk reasoning over…

ProteoKnight: Convolution-based Phage Virion Protein Classification and Uncertainty Analysis

arXiv:2508.07345v2 Announce Type: replace Abstract: \textbf{Introduction:} Accurate prediction of Phage Virion Proteins (PVP) is essential for genomic studies due to their crucial role as structural elements in…

A Pre-Specified Construction-Confirmation Test of Operation-Level Causal Transfer Across Finite Isomorphic Symbolic Domains

arXiv:2608.15809v1 Announce Type: new Abstract: Behavioral accuracy, linear decodability, and successful activation interventions do not by themselves show that a model carries an operation-level structure from one…

Provenance, Not Behaviour: A Serialisation Artifact in Edge-IIoTset and a Leakage-Free Benchmark for Precision-Agriculture Intrusion Detection

arXiv:2608.15761v1 Announce Type: cross Abstract: Edge-IIoTset is the reference benchmark for machine-learning intrusion detection in the industrial Internet of Things, and results reported on it cluster above 99%. We…

Pointer Networks with Q-Learning for Combinatorial Optimization

arXiv:2311.02629v5 Announce Type: replace Abstract: We introduce the Pointer Q-Network (PQN), a hybrid neural architecture that integrates model-free Q-value policy approximation with Pointer Networks (Ptr-Nets) to…

The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks

arXiv:2608.16630v1 Announce Type: cross Abstract: Repository-scale coding requires an agent to keep tests, imports, configuration, and migration rules consistent within a bounded context window. We model this as…

zLend: A Dual-Scope Cash-Flow Reconstruction Framework for On-Chain Credit Underwriting

arXiv:2608.16856v1 Announce Type: cross Abstract: Decentralized lending lacks a credit bureau: a borrower's capacity to repay must be inferred entirely from public on-chain activity, without income verification or a…

Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers

arXiv:2608.14649v1 Announce Type: new Abstract: We present dLLM-SetScore, a training-free method that uses discrete masked-diffusion language models for multi-label text classification. For each candidate label, it asks…

Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings

arXiv:2608.14648v1 Announce Type: cross Abstract: In this study, we revisit three widely used techniques in vector search and utilize them to optimize vector embedding indexing through clustering: dimensionality…

From Recoverability to Functional Use: Auditing Temporal Reports in Time-Series Forecasting

arXiv:2608.10433v4 Announce Type: replace Abstract: Time-series forecasters increasingly accompany numerical predictions with explicit temporal reports, such as delays or selected history, but a correct report need not…

Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions

arXiv:2608.14642v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents trained on a single reward signal exploit the gap between the designed reward and the intended behavior. This is particularly a problem…

DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance

arXiv:2608.14644v1 Announce Type: new Abstract: Real-world LLM deployments increasingly rely on runtime-injected prohibitions--enterprise policies, PII redlines, tool boundaries--that vary per request and per tenant.…

Beyond Effective Sample Size: Effective Number of Proposals for Adaptive Importance Sampling

arXiv:2608.15154v1 Announce Type: cross Abstract: Population-based adaptive importance sampling (AIS) methods use a set of proposal densities to approximate complex target distributions. Their performance is commonly…

A Tree-Structured Approach for Phishing Template and Attacker Attribution Analysis

arXiv:2608.16158v1 Announce Type: new Abstract: Phishing remains a persistent and evolving cybersecurity threat, with attack volumes reaching record levels. This growth is driven by the industrialization of phishing…

Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems

arXiv:2608.15144v1 Announce Type: cross Abstract: Posterior sampling with a pretrained diffusion prior is governed by a conditional score whose intermediate likelihood component is generally intractable. We begin from…

IP Protection in the Era of Visual Generative AI: A Survey

arXiv:2608.14730v1 Announce Type: cross Abstract: The rapid evolution of visual generative AI has introduced a wide range of intellectual property risks, spanning the unauthorized learning, reproduction, extraction,…

Exact Attention Sensitivity and the Geometry of Transformer Stability

arXiv:2602.18849v2 Announce Type: replace Abstract: We develop a sensitivity analysis for transformer attention in a geometry aligned with tokenwise computation. Our main result is the exact identity…

Unsupervised Learning of Cell Instances with Generative Routing Pyramids

arXiv:2608.16810v1 Announce Type: cross Abstract: Identifying and representing object instances such as cells or nuclei is a common task in microscopy image analysis. Established machine learning workflows typically use…

A Deep Learning Model for Spatially Clustered Data via Differentiable Cluster Assignment

arXiv:2608.14968v1 Announce Type: cross Abstract: We consider nonparametric regression when the association between a response and its covariates changes across an unknown partition of a spatial domain. The proposed…

Can Neural Networks Learn by Experimenting on Themselves? Self-Interventional Learning from Functional Consequences to Predictive Self-Knowledge

arXiv:2608.14894v1 Announce Type: new Abstract: Machine-learning systems usually model external data, while their internal functional organization is analyzed by external observers. This work introduces…

Multi-Granularity Sentiment Integration for LLM-Based Multimodal Sentiment Analysis

arXiv:2608.16201v1 Announce Type: new Abstract: Multimodal sentiment analysis (MSA) aims to predict sentiment polarity and intensity from heterogeneous inputs such as text, audio, and vision. While large language models…

A Theoretical Framework for Statistical Evaluability of Generative Models

arXiv:2604.05324v3 Announce Type: replace Abstract: Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d. test data sampled from the ground-truth distribution. In…

Sequential Multimodal Evidence Optimization for Product Media Ranking in E-Commerce

arXiv:2608.15662v1 Announce Type: new Abstract: On modern e-commerce stores, customers consume ordered slates of heterogeneous product media, such as images, videos, and 3D renders, before making purchase decisions.…

LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression

arXiv:2607.03057v2 Announce Type: replace Abstract: The rapid growth in the parameter scale of large language models (LLMs) has created a strong demand for efficient compression techniques. As a hardware-agnostic and…

Spectral Saliency for Machine Unlearning

arXiv:2608.15548v1 Announce Type: new Abstract: Machine unlearning (MU) aims to remove the influence of specific training data while preserving model utility. As the name suggests, MU can be viewed as the inverse of…

Global Federated Learning Strategies for Building Efficient Personalized Models

arXiv:2608.15107v1 Announce Type: new Abstract: Federated learning (FL) is a practical framework that can train models on distributed user data while guaranteeing data privacy; however, due to heterogeneity in which…

Localized TabICLv2: Scaling Tabular In-Context Learning through k-NN

arXiv:2608.16429v1 Announce Type: new Abstract: Foundational models for tabular data have made significant progress in recent years, with TabICLv2 reporting state-of-the-art performance on several tabular classification…

Tail-Aware Top-$k$ On-Policy Distillation

arXiv:2608.14728v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as an effective paradigm for transferring knowledge between language models, where a student is trained to align its next-token…

Functional anatomy of Pythia-Herwig differences with Kolmogorov-Arnold networks

arXiv:2608.15952v1 Announce Type: cross Abstract: Differences between high-energy event generators can arise at several stages of the collision simulation, from the hard scattering through parton showering and…

The Null Token Knows: Reducing Message-Free Hallucination in ASR and NMT

arXiv:2608.15940v1 Announce Type: cross Abstract: Modern encoder-decoder systems can produce fluent text even when their input contains no recoverable message. We study this failure in ASR and NMT through the models'…

Comprehensive language-image pre-training for 3D medical image understanding

arXiv:2510.15042v3 Announce Type: replace-cross Abstract: In the 3D medical image domain, vision-language pre-training is used to create vision-language encoders (VLEs) that can support radiologists by retrieving…

Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems

arXiv:2608.14570v1 Announce Type: new Abstract: Understanding human mobility is critical for a wide range of urban applications, including traffic management, epidemic control, and urban planning. However, due to…

Optimal Lower Bounds for Networked Information Aggregation

arXiv:2608.15472v1 Announce Type: new Abstract: The problem of networked information aggregation, studied in Kearns et al. (2026), involves a group of learners situated on the vertices of a directed acyclic graph $G$,…

Near-Equilibrium Propagation training in nonlinear wave systems

arXiv:2510.16084v3 Announce Type: replace Abstract: Backpropagation learning algorithm, the workhorse of modern artificial intelligence, is notoriously difficult to implement in physical neural networks. Equilibrium…

Temporal Graph Prototype-conditioned Conformal Prediction for Fraud Detection

arXiv:2608.15768v1 Announce Type: new Abstract: Conformal prediction (CP) provides distribution-free coverage guarantees and has emerged as a principled tool for uncertainty quantification. In edge-level fraud detection…

Self-Routed Tensor Adapters for Parameter-Efficient Universal Visual Adaptation

arXiv:2608.16384v1 Announce Type: cross Abstract: Universal visual representations require adaptation mechanisms that adapt across heterogeneous domains without fragmenting knowledge into domain-specific modules.…

ARGUS: Attention-Guided Transformers for Scalable Person Identification Using Wi-Fi Telemetry

arXiv:2608.14670v1 Announce Type: new Abstract: Passive, device-free person identification offers an alternative to camera- and wearable-based biometrics, yet existing wireless approaches rely largely on gait or…

From Uniform to Learned Knots: A Study of Spline-Based Numerical Encodings for Tabular Deep Learning

arXiv:2604.05635v2 Announce Type: replace Abstract: Numerical preprocessing remains a critical component of tabular deep learning, as the representation of continuous features can strongly affect downstream performance.…

LLMs for Zero-Shot Threat Detection via Structured Risk Indicators

arXiv:2608.16508v1 Announce Type: cross Abstract: We propose a two-stage large language model (LLM) framework for zero-shot detection of insider threats and advanced persistent threats (APTs) from heterogeneous security…

CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts

arXiv:2604.10496v2 Announce Type: replace Abstract: Outliers have emerged as a fundamental bottleneck in preserving accuracy for low-precision large models, particularly within Mixture-of-Experts (MoE) architectures…

Learning to Unlearn: Machine Unlearning via Learning the Unlearning Behaviors

arXiv:2608.16700v1 Announce Type: new Abstract: Various machine unlearning techniques have been developed in response to privacy legislation requirements, enabling individuals to exercise their legal right to have their…

Ring-based Spatial Transformer: Learning Non-linear Spatial Interactions between Building Distribution and Pedestrian Flow

arXiv:2608.14660v1 Announce Type: new Abstract: This study proposes a ring-based SpatialTransformer to learn how building uses at different distances from a railway station interact to generate pedestrian flow.…

NeuRoute: Logit-Guided Neural Routing for Billion-Scale Vector Search with Sub-Hour Index Construction

arXiv:2608.15438v1 Announce Type: cross Abstract: Building approximate nearest neighbor (ANN) indexes at billion scale is often dominated by expensive global clustering or graph construction, making time-to-index a…

Federated Self-Supervised Modulation Classification under Non-IID and Imbalanced Data

arXiv:2510.04927v2 Announce Type: replace Abstract: Automatic modulation classification (AMC) is a core enabler of cognitive wireless systems, providing spectrum awareness and supporting adaptive communication at the…

Learning Generalizable Reconstruction of High-Dimensional Neural Dynamics

arXiv:2608.16569v1 Announce Type: new Abstract: Accurate reconstruction of long-duration neural recordings is challenging because local field potentials (LFPs) are high-resolution, multichannel, transient, and variable…

Fiber Fingerprints of Hidden Learning-State Dynamics

arXiv:2608.15976v1 Announce Type: new Abstract: A learning system can occupy execution states that are indistinguishable under every declared present-behavior readout yet respond differently to future training. We…

REFLEX: Reflexive Equilibrium Fixed-point Learning for Endogenous eXchanges

arXiv:2608.16155v1 Announce Type: new Abstract: In over-the-counter corporate bond markets, dealers compete for client trades by quoting bid and ask prices. Tighter quotes attract more business, but also informed…

Encoding of musical structures in hidden units of restricted Boltzmann machines

arXiv:2509.04899v4 Announce Type: replace-cross Abstract: Restricted Boltzmann machines (RBMs) are energy-based models originating from statistical physics, in which hidden units mediate the probability distribution of…

Protein Structure Prediction: From Evolutionary Constraints to Generative Modeling

arXiv:2608.16094v1 Announce Type: cross Abstract: Accurate protein structure prediction is fundamental to structural biology because protein structure underlies molecular function and provides a basis for mechanistic…

Degeneracy Counting Quantum Algorithm using Decoherence

arXiv:2608.14941v1 Announce Type: new Abstract: Counting the global optima of a classical optimization problem is a #P-hard task. We develop the canonical thermal pure quantum (CTPQ) state-based degeneracy counting…

Balancing Optimality and Diversity: Human-Centered Decision Making through Generative Curation

arXiv:2409.11535v3 Announce Type: replace Abstract: Many decision-support systems recommend actions by optimizing measurable objectives, even when a human decision-maker retains final authority and considers additional…

Temporal Logic Guided Universal Task Representations for Reinforcement Learning

arXiv:2608.15509v1 Announce Type: cross Abstract: Task guided agents demonstrate strong performance in a wide range of complex tasks. However, most existing task representation algorithms are tailored to specific…

Towards a theory of inference-time alignment with unknown rewards

arXiv:2608.15402v1 Announce Type: new Abstract: Generative model alignment has received broad interest, and significant progress has been made in supervised fine-tuning and inference-time computation. Yet, alignment has…

Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivarianc

arXiv:2608.14556v1 Announce Type: new Abstract: Physical fields on meshes require a separation between topology and geometry: conservation laws are topological and should be exact, while geometry, material response, and…

STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation

arXiv:2608.14861v1 Announce Type: cross Abstract: Data poisoning attacks pose serious security threats to Federated Learning (FL) systems in Computer Vision. Despite growing research attention, two key challenges remain…

CFR without Unbiasedness: Deterministic Guarantees for Persistent Public-Chance Schedules

arXiv:2608.14761v1 Announce Type: cross Abstract: At a finite public-chance cut, counterfactual regret minimization (CFR) must choose how many outcomes to evaluate before each regret update. Exact evaluation processes…

PRO-Bid: Pareto-Prioritized Regret Optimization for Constraint-Aware Generative Auto-Bidding

arXiv:2602.08261v2 Announce Type: replace Abstract: Auto-bidding systems strive to maximize marketing value while maintaining high compliance with efficiency constraints, such as Target Cost-Per-Action (CPA). While…

Correlation Clustering with Random Partial Information

arXiv:2608.16315v1 Announce Type: cross Abstract: Correlation clustering is a fundamental unsupervised learning problem. On complete graphs, both the min-disagreement and min-max objectives admit constant-factor…

ODTlearn: A Package for Learning Optimal Decision Trees for Prediction and Prescription

arXiv:2307.15691v4 Announce Type: replace-cross Abstract: ODTlearn is an open source Python package that provides methods for learning optimal decision trees for high-stakes predictive and prescriptive tasks based on…

FAST-DeepONet: Factor-Augmented Branch Representations for High-Dimensional PDE Inputs in the Small-Sample Regime

arXiv:2608.15408v1 Announce Type: new Abstract: Deep operator networks can become statistically unstable when partial differential equation inputs are observed at thousands of strongly correlated sensors but only a…

Differentiable Thermodynamic Phase-Equilibria for Machine Learning

arXiv:2603.11249v4 Announce Type: replace Abstract: Accurate prediction of phase equilibria remains a central challenge in chemical engineering. Physics-consistent machine learning methods that incorporate thermodynamic…

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

arXiv:2607.10139v3 Announce Type: replace Abstract: Selecting the correct answer from a pool of candidate reasoning chains is the engine of test-time scaling, yet the standard selectors each carry a cost:…

Leveraging Generative Artificial Intelligence for Causal Inference with Unstructured Data

arXiv:2507.03897v4 Announce Type: replace Abstract: We introduce GenAI-Powered Inference (GPI), a statistical framework for both causal and predictive inference using unstructured data, including text and images. GPI…

Efficient Neural-Network-Based High-Resolution Radiative Transfer for CO___ Retrieval, and Application to Interferometric Sensing

arXiv:2608.14645v1 Announce Type: new Abstract: Studying climate change requires reducing uncertainties in CO2 and CH4 emission estimates to better distinguish anthropogenic from natural sources, which motivates…

Digital Twin Degradation: Detecting Cyber Physical Attacks via Temporal Inconsistencies

arXiv:2608.16159v1 Announce Type: cross Abstract: Digital Twins (DTs) are increasingly used to monitor and analyze Cyber Physical Systems (CPS). However, in adversarial environments, the fidelity of a DT cannot be…

Learning Varying Physical Therapist-Patient Interactions for Robot-mediated Upper Limb Task-Specific Training

arXiv:2608.15995v1 Announce Type: cross Abstract: Upper extremity motor function recovery is positively linked to Task-Specific Training (TST) and sufficient therapy dosage. Rehabilitation robots can increase TST dosage…

An Analytical-Prior Framework for Data-Efficient Prediction of Sound-Reduction Frequencies in Rectangular Side-Branch Helmholtz Resonators

arXiv:2608.16873v1 Announce Type: new Abstract: High-fidelity finite-element simulations can provide accurate numerical predictions for side-branch resonators, but large simulation datasets are expensive to generate and…

On Fibonacci Ensembles: An Alternative Approach to Ensemble Learning Inspired by the Timeless Architecture of the Golden Ratio

arXiv:2512.22284v2 Announce Type: replace-cross Abstract: Nature rarely reveals her secrets bluntly, yet in the Fibonacci sequence she grants us a glimpse of her quiet architecture of growth, harmony, and recursive…

NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption

arXiv:2608.16038v1 Announce Type: new Abstract: Post-hoc Graph Neural Network (GNN) explainers commonly follow a Perturb-Query paradigm, inferring the importance of graph elements based on queried predictions to…

DeepOHeat-v2: Self-Improving Operator Learning for Fast and Trustworthy Thermal Optimization in 3D-IC Design

arXiv:2608.16080v1 Announce Type: new Abstract: Thermal-aware optimization of multi-die 3D integrated circuits evaluates many designs, each a costly heat-equation solve. Operator-learning surrogates replace this solve…

DeltaLog: Deferred Materialization of Recurrent States for Linear Attention Decoding

arXiv:2608.15533v1 Announce Type: cross Abstract: Linear attention models eliminate the quadratic prefix computation and context-growing KV cache of softmax attention by replacing pairwise token interactions with…

Q-Regularized Generative Auto-Bidding: From Suboptimal Trajectories to Optimal Policies

arXiv:2601.02754v3 Announce Type: replace Abstract: With the rapid development of e-commerce, auto-bidding has become a key asset in optimizing advertising performance under diverse advertiser environments. The current…

Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents

arXiv:2605.28850v3 Announce Type: replace Abstract: We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments. TradeArena, an auditable…

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching

arXiv:2412.18911v3 Announce Type: replace Abstract: Diffusion Transformers (DiT) have become the dominant methods in image and video generation yet still suffer substantial computational costs. As an effective approach…

GOD: Enhancing Generalization via Deep Grafting for Sequential Recommendation

arXiv:2608.16073v1 Announce Type: cross Abstract: Sequential recommenders often struggle with sparse and noisy histories, limiting generalization to unseen interactions. Knowledge distillation mitigates this by…

Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning

arXiv:2608.14706v1 Announce Type: cross Abstract: Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting…

Fast Test-Time Refinement for Robust Learned Image Compression

arXiv:2608.15113v1 Announce Type: cross Abstract: Learned image compression (LIC) has demonstrated remarkable rate-distortion (RD) performance in benign settings. However, the high representational capacity endowed by…

When to Communicate: Belief Distributions and KL Divergence for Principled Gating in Multi-Agent RL

arXiv:2608.14559v1 Announce Type: cross Abstract: Effective communication in multi-agent reinforcement learning requires agents to decide not only \textit{what} to communicate, but when? Existing approaches either…

DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations

arXiv:2405.07780v3 Announce Type: replace Abstract: This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We…

Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation

arXiv:2608.15660v1 Announce Type: cross Abstract: Federated learning (FL) enables privacy-preserving distributed model training but faces challenges from heterogeneous model architectures and limited communication…

Graph Machine Learning: An Opportunity for Power Systems

arXiv:2608.16494v1 Announce Type: new Abstract: Modern power systems face growing operational complexity driven by the integration of renewable energy sources, decentralization, and the need for real-time…

6G Native AI and Channel Foundation Models

arXiv:2608.14591v1 Announce Type: cross Abstract: The integration of artificial intelligence (AI) and wireless communications is widely regarded as a core objective of sixth-generation (6G) systems. However, both the…

Mint-Agent: Introducing Finance-Native Agentic Foundation Models

arXiv:2608.16386v1 Announce Type: cross Abstract: Financial agents must do more than recall domain knowledge: they must be both reliable, executing precise operations over grounded evidence, and executive, sustaining…

Measuring Structured Predictability in Neural Training Dynamics: A Cross-Regime Study

arXiv:2608.15483v1 Announce Type: new Abstract: Modern deep networks are trained through long update trajectories, yet their temporal organization remains less systematically characterized than architectures, losses, or…

The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution

arXiv:2605.27599v3 Announce Type: replace Abstract: Agentic AI workloads - where a single user goal triggers multi-step orchestration, tool calls, retries, and failure recovery - are being targeted for edge deployment,…

SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA

arXiv:2509.25459v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) show promise in generating long-form scientific explanations that synthesize evidence and connect multiple factors. However, in…

Offline Ambient-Controlled Latent Diffusion: Architecture, Telemetry, and On-Device Evaluation

arXiv:2608.14677v1 Announce Type: cross Abstract: Most mobile image-generation applications are thin clients over cloud services, leaving outputs hard to audit. We present an Android latent-diffusion application that…

Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations

arXiv:2603.14894v3 Announce Type: replace Abstract: Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations. Post-hoc…

PureTD: Reinforcement Learning for Backgammon Money Games with No Evaluation-time Search

arXiv:2608.15146v1 Announce Type: new Abstract: We revisit Tesauro's TD-Gammon for backgammon money games in the setting of no evaluation-time search. Both checker play and cube action (use of the doubling cube) are…

Is Grokking a Loss of Normal Hyperbolicity of the Interpolation Manifold?

arXiv:2608.14803v1 Announce Type: new Abstract: A recent line of work recasts the post-memorization phase of grokking as constrained optimization: once a network interpolates the training set, weight decay drives a slow…

ConfRetro: a 3D-aware template-free method for enhancing retrosynthesis via molecular conformer information

arXiv:2501.12434v3 Announce Type: replace Abstract: Motivation: Retrosynthesis plays a crucial role in organic synthesis and drug discovery, focusing on identifying a set of reactants capable of synthesizing a target…

Hardware-in-the-Loop Phase-Aware CNN for Real-Time 5G Channel Estimation

arXiv:2608.14709v1 Announce Type: cross Abstract: This demo presents real-time AI-based uplink channel-estimation inference using data collected from a hardware-in-the-loop 5G platform. The data-collection setup…

Bringing Generative Learning to Representation Learning: Self-Supervised Transfer Learning as Distribution Matching

arXiv:2502.14424v3 Announce Type: replace-cross Abstract: Most self-supervised learning objectives defend against collapse but leave the target representation law unspecified. We formulate representation learning as…

FETERS: Few-Shot Early Time-Series Classification via Effective Ratio Selection

arXiv:2608.16385v1 Announce Type: new Abstract: Early time-series classification (ETSC) aims to make accurate predictions from partially observed time series as early as possible. Although various stopping mechanisms…

Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs

arXiv:2602.12756v2 Announce Type: replace Abstract: Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting (TSF), leveraging their inherent sequential reasoning capabilities to…

BrainLinear: A Linear Model for Brain Network Analysis in Sparse Tangent Subspaces

arXiv:2608.15266v1 Announce Type: cross Abstract: Functional connectome analysis examines brain-region interactions to understand and identify disorders such as autism spectrum disorder and Alzheimer's disease. Existing…

Speculative Rollback Correction for Quality-Diverse Web Agent Imitation

arXiv:2606.12485v2 Announce Type: replace Abstract: Training interactive web agents through imitation learning from expert trajectories has emerged as a highly effective approach. However, determining the optimal timing…

Shape Operator PCA: Curvature-Aware Projections for Geometric Machine Learning

arXiv:2608.15313v1 Announce Type: new Abstract: In this paper, we propose SHOPCA (Shape Operator-based Principal Component Analysis), a novel method for unsupervised metric learning and dimensionality reduction that…

iFuzz-Meta: An Interpretable Fuzzy Learning Framework Bridging Top-Down and Bottom-Up Knowledge Integration

arXiv:2608.14646v1 Announce Type: new Abstract: Interpretable representation learning remains a key challenge in modern neural computation, particularly when models are expected not only to perform but also to explain…

BERTopic-Virality Prioritisation: A Scalable Framework for Thematic and Comparative Analysis of COVID-19 and Monkeypox Misinformation on Twitter

arXiv:2608.15691v1 Announce Type: cross Abstract: Health misinformation circulating during pandemics can gain traction rapidly, creating harmful narratives that compete with public health guidance. Most topic-modelling…

Global Convergence of DGM and PINN Algorithms for Solving Nonlinear PDEs

arXiv:2607.24726v2 Announce Type: replace Abstract: The Deep Galerkin Method (DGM) and Physics Informed Neural Networks (PINNs) have become widely-used methods for solving partial differential equations (PDEs) in the…

Coded Hankel Polynomial Chaos: Spectral Identification of Dominant Polynomial-Chaos Modes

arXiv:2608.16126v1 Announce Type: cross Abstract: Identification of dominant polynomial-chaos modes is usually formulated as a sparse-regression problem on a sampled multivariate polynomial dictionary. We develop coded…

Probability-Preserving Transformer for the Time-Dependent Schr\"odinger Equation

arXiv:2608.15112v1 Announce Type: new Abstract: Solving the time-dependent Schr\"odinger equation (TDSE) via traditional numerical methods is computationally intensive. Transformer models offer a compelling alternative,…

Probabilistic Circuits as Reasoning Machines in Artificial Intelligence (Part I)

arXiv:2608.16565v1 Announce Type: cross Abstract: This cumulative habilitation thesis studies probabilistic circuits (PCs) as a powerful and tractable framework for reasoning and learning under uncertainty in artificial…

LaGSplat: Inferring Physics-Governed Interactive Simulation from Monocular Video Using Latent Lagrangian Gaussian Splatting

arXiv:2608.16324v1 Announce Type: cross Abstract: We present LaGSplat (Latent Lagrangian Gaussian Splatting), a framework that infers interactive, physics-governed dynamics from one or a few monocular videos. At…

RadioVIL: Anomaly-Aware Diffusion Models for Radio Map Inpainting and Zero-Shot Vehicle Localization

arXiv:2608.16167v1 Announce Type: cross Abstract: High-precision radio map construction is essential for emerging 6G Integrated Sensing and Communication (ISAC) applications, including digital twins and intelligent…

Neurai-VN Benchmark: Standardized Machine Learning Models for Multimodal Digital Phenotyping in Mental Health Classification

arXiv:2607.25232v3 Announce Type: replace Abstract: Digital phenotyping (DP) using smartphones and wearable devices has emerged as a promising approach for assessing mental health, particularly depression and anxiety.…

Domain-Agnostic Neural Topic Modeling with Contextual Token-Level Semantic Graph Representation

arXiv:2608.16269v1 Announce Type: cross Abstract: Recent advances in neural topic models with pre-trained language models (PLMs) have achieved strong performance by leveraging general-domain pre-training, yet their…

SCPP: A Unified Python Library for Soft Clustering

arXiv:2607.19620v2 Announce Type: replace Abstract: In this paper, we present SCPP (Soft Clustering Python Package), an open-source Python framework for soft clustering. SCPP establishes a canonical,…

Beyond Peak Backlog: Conditional Energy and Temporal Geometry in Capacity-Constrained Delayed Bandit Optimization

arXiv:2608.16216v1 Announce Type: new Abstract: What is the right delay complexity when a learner can track only $C$ pending feedback items and discarded feedback is permanently lost? Existing one-point bandit convex…

Convolution-Free Holistic Multivariance Decomposition Layer for Efficient Hyperspectral Image Classification Tensor Networks

arXiv:2608.16241v1 Announce Type: cross Abstract: Feature extraction for hyperspectral image classification is conventionally addressed using rigid tensor decompositions that fail to capture complex spatio-spectral…

Fractional Optimizers Meet Fractal Activation Functions: An Empirical Study of Multi-Scale Optimization in Neural Network

arXiv:2608.14636v1 Announce Type: new Abstract: Fractional optimization methods and fractal activation functions are two independent directions for improving neural network training. Fractional optimizers extend…

WANDR: A Benchmark for Wide and Deep Research

arXiv:2608.14747v1 Announce Type: new Abstract: WANDR (Wide ANd Deep Research) is a benchmark of 500 realistic, challenging data-collection tasks for research agents. Each task requires a system to discover a large set…

Task-Anchored Representation Shaping for Pre-Trained Model-Based Continual Learning

arXiv:2608.16345v1 Announce Type: new Abstract: Pre-trained models (PTMs) provide a strong foundation for continual learning by offering stable representations that facilitate lightweight adaptation to new tasks.…

Domain-Specific Text Embedding Models for Entity Resolution

arXiv:2608.16161v1 Announce Type: cross Abstract: General-purpose text embedding models are designed to capture semantic similarity but are not optimised for distinguishing entity records that represent the same…

Population Structure Analysis of an Inbred Population using Quantitative Shape Phenotyping from Stereo Retinal Photographs

arXiv:2608.15471v1 Announce Type: new Abstract: The population structure of an inbred population of 781 people on Norfolk Island in the Pacific, 318 of which are descendants of the original Mutineers of the Bounty, is…

On Stopping Times of Power-one Sequential Tests: Tight Lower and Upper Bounds

arXiv:2504.19952v2 Announce Type: replace-cross Abstract: We present two general lower bounds for stopping times of sequential tests between arbitrary composite nulls $\mathcal P$ and alternatives $\mathcal Q$. The…

MiNO: Cotangent-bundle propagator learning for PDEs

arXiv:2608.15187v1 Announce Type: new Abstract: Scientific machine learning for partial differential equations commonly targets solution fields, as in physics-informed neural networks, or solution maps, as in neural…

A Unified Geometric Framework for Developmental Analysis of Spatial Transcriptomic Data

arXiv:2608.15306v1 Announce Type: cross Abstract: High-throughput single-cell and spatial transcriptomic technologies provide high-resolution snapshots of heterogeneous cellular states, but their destructive nature…

Workspace Topology as an Attack Vector in Agentic Coding Assistants

arXiv:2608.14876v1 Announce Type: cross Abstract: Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code. This opens up a risk of…

Information Geometry of Message Passing

arXiv:2608.15922v1 Announce Type: new Abstract: We show that the natural-gradient stationary condition of variational inference has an edge-local form on a Forney-style factor graph. We start from the Bethe free energy…

QSMP: finding representative time series subsequences through Quick Shift+Matrix Profile

arXiv:2608.15492v1 Announce Type: new Abstract: Finding representative waveforms in long time series has scientific and practical value in many domains, as it enables summarization and visualization of large time series…

Enhancing Differentially Private Linear Regression via Public Second-Moment

arXiv:2508.18037v2 Announce Type: replace Abstract: Leveraging information from public data has become increasingly crucial in enhancing the utility of differentially private (DP) methods. Traditional DP approaches…

Spinning Conformal Correlators from Neural Networks

arXiv:2608.15001v1 Announce Type: cross Abstract: We construct spinning conformal fields from neural networks and the embedding formalism, computing their two-, three- and four-point functions in examples, building on…

Prediction Inference of Time Series with Standard ReLU Deep Neural Networks

arXiv:2608.15362v1 Announce Type: cross Abstract: We propose a methodology based on the standard ReLU Deep Neural Networks (DNN) to make predictions and quantify their uncertainty. Classically, people rely on linear,…

Explaining Reinforcement Learning Decisions in Self-adaptive Systems

arXiv:2608.14620v1 Announce Type: new Abstract: Reinforcement Learning (RL) has been extensively used in autonomous and self-* systems, but RL policies, especially deep RL ones relying on neural networks, lack…

Zero-Shot Adaptation of Medical Vision Foundation Models for High-Frequency Micro-Ultrasound Prostate Segmentation

arXiv:2608.14796v1 Announce Type: cross Abstract: Prostate cancer claims a life every 80 seconds. Early detection is needed to prevent disease progression, and both PSA density calculation and biopsy decisions rely on…

Which Question Is Your Attention Metric Answering? Attention Rows as Compositional Data

arXiv:2608.14712v1 Announce Type: cross Abstract: Each row of a transformer's attention matrix is a probability distribution over tokens, and in trained models most of that probability lands on a single \emph{sink}…

Quantifying Depth Sufficiency in Residual Neural Networks: A First-Order Criterion

arXiv:2608.14664v1 Announce Type: new Abstract: How can we determine whether a trained neural network is already deep enough? We study this under a fixed function-preserving residual-growth protocol specifying insertion…

Model Inversion Attacks: A Survey of Approaches and Countermeasures

arXiv:2411.10023v3 Announce Type: replace Abstract: Deep neural networks have enabled numerous studies and applications on both Euclidean data, such as images and text, and non-Euclidean data, such as graphs. Because…

Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs

arXiv:2509.16586v2 Announce Type: replace Abstract: Recent advances have significantly improved our understanding of the sample complexity of learning in average-reward Markov decision processes (AMDPs) under the…

Spectral Gaps of Hit-and-Run and Coordinate Hit-and-Run

arXiv:2608.16878v1 Announce Type: cross Abstract: For any convex body $\mathcal{K}\subset\mathbb{R}^{n}$ containing a unit ball, the spectral gap of Hit-and-Run is $\Omega(1/(n^2 C_{\mathsf{PI}}))$, where…

ROC-n-reroll: How verifier imperfection affects test-time scaling

arXiv:2507.12399v3 Announce Type: replace Abstract: Test-time scaling aims to improve language model performance by leveraging additional compute during inference. Many works have empirically studied techniques such as…

Beat the Counter First: A Baseline for Temporal-Graph Anomaly Detectors

arXiv:2608.15965v1 Announce Type: new Abstract: Progress in streaming, edge-level graph anomaly detection (GAD) has been marked by increasingly elaborate architectures, from count-min-sketch chi square tests to…

A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification

arXiv:2608.14824v1 Announce Type: cross Abstract: We present a parameter-free episodic evaluation of nearest-centroid classification for elephant vocalisations on fixed pretrained acoustic embeddings, across the…

PhyxMamba: Chaotic System Reconstruction from Short Context Observations with Generative State-Space Models

arXiv:2505.23863v3 Announce Type: replace Abstract: Understanding chaotic dynamics is a fundamental problem across scientific disciplines, including climate science, neuroscience, and fluid dynamics, yet direct…

Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling

arXiv:2608.14652v1 Announce Type: new Abstract: The development of 0.1$^{\circ}$ global weather forecasting models based on machine learning (ML) is constrained by the limited availability of high-resolution data, as…

Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization

arXiv:2606.17215v2 Announce Type: replace Abstract: A certificate that removes outliers sees the data only through its low-degree moments, and an adversary exploits exactly this, hiding corruption where the clean data…

Decorrelation Is Not Complementarity: Skill, Not Lineage, Governs Trusted-Monitor Ensembles

arXiv:2608.16190v1 Announce Type: cross Abstract: Trusted monitoring has a cheap, trusted model score a stronger untrusted model's actions, and a diverse ensemble of them beats a single stronger monitor at matched cost.…

Multi-Bin Batching for Increasing LLM Inference Throughput

arXiv:2412.04504v2 Announce Type: replace-cross Abstract: As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly…

RigidBench: Evaluating Rigid-Body Physics in Video Generation Models

arXiv:2608.15555v1 Announce Type: cross Abstract: Video models are increasingly used to predict what happens next in a scene, yet the metrics commonly used to compare their outputs say little about whether the predicted…

Towards Reasonable Molecular Structure Elucidation from Infrared Spectroscopy with Chemical Feedback

arXiv:2608.16082v1 Announce Type: new Abstract: Infrared (IR) spectra provide characteristic signals of molecular structure, which are often interpreted by experts via functional-group identification or library…

Mitigating Rubric Interference in LLM Judges via On-Policy Self-Distillation

arXiv:2608.14684v1 Announce Type: new Abstract: LLM judges increasingly evaluate responses against fine-grained rubric checklists. When a sample requires multiple rubrics, current methods typically assess each in a…

P2E-VQ: ECG-linked representation augmentation for PPG via discrete patch retrieval

arXiv:2608.14656v1 Announce Type: new Abstract: Photoplethysmography (PPG) is widely used in consumer wearables because of its low cost and ease of acquisition. However, unlike electrocardiography (ECG), PPG measures…

Global Simulation-Guided Dynamic Operator Scheduling for Efficient Multi-Tenant Model Serving

arXiv:2608.15762v1 Announce Type: cross Abstract: Container-granularity scheduling leaves abundant short-lived idle slices within containers unexploited. Reallocating containers is too heavyweight to utilize such…

Scaling Laws for Dynamic Mini-Batch SGD in Sketched Linear Regression

arXiv:2605.24316v3 Announce Type: replace Abstract: Mini-batching is central to large-scale optimization, yet its role in statistical scaling laws remains limited. We study one-pass and multi-pass batch SGD for sketched…

Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface

arXiv:2608.16134v1 Announce Type: new Abstract: In clinical motor imagery brain-computer interface (MI-BCI) decoding, cross-day transferability and online operation remain two critical challenges. Hypergraphs can…

FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction

arXiv:2608.15727v1 Announce Type: new Abstract: Diffusion models have recently shown strong potential for multivariate time-series anomaly detection by learning the distribution of normal data through iterative…

AMPLIFAI: A Multiphase CT Dataset for Benchmarking Clinical Reasoning in LI-RADS Assessment of Liver Lesions

arXiv:2608.14778v1 Announce Type: cross Abstract: Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related mortality worldwide, with early detection improving survival from <20\% to >70\%. The…

Joint MDPs and Reinforcement Learning in Coupled-Dynamics Environments

arXiv:2603.06946v2 Announce Type: replace Abstract: Many distributional quantities in reinforcement learning are intrinsically joint across actions, including distributions of gaps and probabilities of superiority.…

Unifying Graph Neural Networks Through a Common Layer Equation

arXiv:2608.16097v1 Announce Type: new Abstract: Graph neural networks are commonly described through family-specific equations whose notation obscures shared computations and structural differences. We introduce a…

Auxiliary uncertainty signals for LLM-assisted systematic review screening: a benchmark across eight Cohen drug-class reviews

arXiv:2608.14551v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for title-abstract screening in systematic reviews, but their decisions lack calibrated uncertainty. We show that an…

SCALE: State-Calibrated Latent Embeddings for JEPA Planning in the Right Geometry

arXiv:2608.16287v1 Announce Type: new Abstract: Joint-embedding predictive world models plan by scoring predicted terminal embeddings against a goal embedding using a cost defined on the representation itself. Two…

Time-Aware Validation of Machine Learning Fuel Consumption Models: Evidence from 1\,Hz Operational Data, CCGS \textit{Sir Wilfrid Laurier}

arXiv:2608.16833v1 Announce Type: new Abstract: Ship fuel consumption (SFC) prediction supports vessel operation optimisation, emissions estimation, and decision support systems (DSS) for sustainable maritime…

In Defense of OCTA: The Reconstruction-Utility Gap in OCT-to-OCTA Synthesis

arXiv:2608.15626v1 Announce Type: new Abstract: Optical coherence tomography angiography (OCTA) images retinal blood flow, giving capillary-perfusion and foveal-avascular-zone biomarkers that grade diabetic-retinopathy…

MoE-Enhanced Explainable Deep Manifold Transformation for Complex Data Embedding and Visualization

arXiv:2410.19504v3 Announce Type: replace Abstract: Dimensionality reduction (DR) plays a crucial role in various fields, including data engineering and visualization, by simplifying complex datasets while retaining…

Guaranteed Adaptive Modality Acquisition: When the Policy Chooses Its Own Calibration Group

arXiv:2608.15520v1 Announce Type: new Abstract: A multimodal system may begin inference holding only some of its inputs and may acquire the rest at a cost. With adaptive acquisition, the policy determines which inputs…

Feasible and Novel Synthetic Population Generation with Tabular and Sequential Travel Attributes

arXiv:2608.15867v1 Announce Type: new Abstract: Synthetic populations are critical inputs for activity-based travel demand models, yet generating realistic populations from limited survey data remains challenging. Small…

Maintaining IoT Device Identification under Concept Drift via Budget-Aware Traffic Labeling

arXiv:2608.15465v1 Announce Type: cross Abstract: Identification of IoT device types from passive traffic is increasingly used for security management in enterprise and ISP networks. However, the performance of machine…

QuantumPhaseNet: A Gauge-Covariant Geometric and Quantum-Spectral Theory of Semantic Concept Hierarchies with Prototype Validation of a Classical Quantum-Inspired Model

arXiv:2608.15820v1 Announce Type: cross Abstract: We present QuantumPhaseNet, a gauge-covariant geometric and quantum-spectral extension of Transformer representations. Context-dependent semantic states are modeled as…

Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation

arXiv:2608.14594v1 Announce Type: new Abstract: Projected Gradient Descent (PGD) is widely used to evaluate adversarial robustness, typically via final adversarial accuracy, which does not capture model behaviour…

OceanDepths: A Global Dataset of Paired Subsurface and Surface Ocean Observations

arXiv:2608.16373v1 Announce Type: new Abstract: Despite comprising over 70\% of its surface, the world's oceans are critically underobserved compared to the land surface or the atmosphere.Understanding the global ocean…

Rethinking Reverse KL as Adaptive Entropy Distillation

arXiv:2608.14685v1 Announce Type: new Abstract: Knowledge distillation (KD) is widely used to transfer the capabilities of large language models (LLMs) to smaller students, but existing objectives often struggle to…

SAPE: Sandwich Adapters for Parameter Efficiency in Large Language Model Fine-Tuning

arXiv:2608.15360v1 Announce Type: new Abstract: While Parameter-Efficient Fine-Tuning (PEFT) has substantially reduced the hardware cost of adapting Large Language Models (LLMs) by decreasing the number of trainable…

A Banach-Space Theory of Markovian Halpern Iteration for Non-Expansive Maps

arXiv:2608.15966v1 Announce Type: new Abstract: We study stochastic approximation of fixed points of a non-expansive operator when the oracle samples originate from a continuing Markovian trajectory. A direct…

Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis

arXiv:2511.11439v3 Announce Type: replace Abstract: Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics. However, the performance often degrades as threat…

Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant

arXiv:2608.15881v1 Announce Type: new Abstract: The Multiphysics Object-Oriented Simulation Environment (MOOSE) is an open-source finite-element framework for building multiphysics simulation applications. Using a…

GraniKV: Asymmetric Granularity KV-Cache Paging for Multi-Agent Systems with Long Shared Prefix

arXiv:2608.15584v1 Announce Type: new Abstract: Production paged-serving engines apply uniform paging granularity to the KV cache, even though the two regions of a multi-agent workload have opposite storage…

FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens

arXiv:2506.03096v2 Announce Type: replace-cross Abstract: Contrastive language-image pre-training aligns features of text-image pairs in a common latent space via distinct encoders for each modality. While this approach…

A Vision Transformer for ECG-Based Detection of Left Ventricular Systolic Dysfunction Across Multiple Clinical Sites

arXiv:2608.14723v1 Announce Type: cross Abstract: Reduced left ventricular ejection fraction (LVEF) is frequently asymptomatic and often detected only after advanced heart failure develops. Electrocardiograms are…

Eigenanalysis framework for autoregressive neural emulators of multi-scale chaotic dynamics

arXiv:2608.16084v1 Announce Type: cross Abstract: Neural autoregressive models have rapidly emerged as powerful emulators of high-dimensional chaotic systems, yet their long-term instability and error growth remain…

Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters

arXiv:2608.14792v1 Announce Type: cross Abstract: Objectives: To determine whether zero-shot prompting of a large language model (LLM) is sufficient to detect shared decision-making (SDM) behaviors in real clinical…

Privacy-Preserving Dataset Curation for Kuala Lumpur Urban Traffic: Grounded Vision-Language Detection with Spatial Vehicle-Context Filtering

arXiv:2608.14724v1 Announce Type: cross Abstract: The rapid advancement of intelligent transportation systems and autonomous driving relies heavily on multi-modal urban traffic datasets. However, curating high-fidelity…

Learning Stock Trading Policies via Barycenter-Based Adversarial Inverse Reinforcement Learning

arXiv:2608.15770v1 Announce Type: new Abstract: Designing effective trading strategies using reinforcement learning remains challenging due to delayed and noisy rewards, poor exploration, and the difficulty of enforcing…

Breaking the Compression Barrier: Cross-Architecture Compression Boundary Learning via Reverse Regrowth

arXiv:2608.16010v1 Announce Type: new Abstract: Model compression is critical for deploying networks on resource-constrained edge devices. While pruning-based methods can significantly reduce model size, they often…

A Privacy Study of Sparse Collaborative Inference

arXiv:2608.16236v1 Announce Type: new Abstract: Collaborative inference (CI) splits a model between an edge device and a server, whereby the client computes an intermediate activation, transmits it, and the server…

Decision-Driven Regularization: A Blended Model for Learning and Optimization

arXiv:2608.15124v1 Announce Type: new Abstract: In contextual optimization, the decision-maker seeks optimal decisions to minimize a cost function, that varies based on observed features. This context is common in many…

SAUL: Sharpness-Aware Augmented-Lagrangian Unlearning

arXiv:2608.16249v1 Announce Type: new Abstract: Machine unlearning in Large Language Models (LLMs) faces a critical trade-off between erasing target knowledge and preserving general utility. We propose SAUL…

TokenSTFormer: A Tokenized Spatial-temporal Attention Model for Holistic Motion Analysis in Adolescent Idiopathic Scoliosis Screening

arXiv:2608.16122v1 Announce Type: cross Abstract: Adolescent Idiopathic Scoliosis (AIS) is a prevalent spinal deformity in adolescents that, if left untreated, can result in severe health outcomes. Traditional screening…

Invariant Pretraining for Robust Code Representations

arXiv:2608.15412v1 Announce Type: new Abstract: Encoder-based code representation models remain widely deployed for discriminative tasks such as clone detection and code classification, where their small size and low…

Multilook Coherent Imaging: Theoretical Guarantees and Algorithms

arXiv:2505.23594v2 Announce Type: replace-cross Abstract: Multilook coherent imaging is a widely used technique in applications such as digital holography, ultrasound imaging, and synthetic aperture radar. A central…

Le Critique: Privileged Value Functions for LLM Reinforcement Learning

arXiv:2608.16739v1 Announce Type: new Abstract: Reinforcement learning algorithms for Large Language Models (LLMs) are largely distinguished by their variance reduction strategy. Group-relative methods like GRPO reduce…

Certifying Compressed Language Models: An Audit and a Statistical Toolkit

arXiv:2608.15046v1 Announce Type: new Abstract: A fraction of a point of benchmark accuracy is the usual evidence that a compressed model is equivalent to its original. That quantity is least informative when two models…

Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics

arXiv:2608.16182v1 Announce Type: new Abstract: Deep Q-learning (DQL) has achieved remarkable empirical success in reinforcement learning, yet its training process remains notoriously unstable. Existing studies often…

ShadowNet for Data-Centric Quantum System Learning

arXiv:2308.11290v2 Announce Type: replace-cross Abstract: Understanding the dynamics of large quantum systems is hindered by the curse of dimensionality. Statistical learning offers new possibilities in this regime…

Longitudinal and Graph-Augmented Prediction of Adolescent Substance Use Onset in the ABCD Study

arXiv:2608.14578v1 Announce Type: cross Abstract: Early identification of adolescent substance-use risk is an important prevention challenge, yet the relative value of baseline characteristics, longitudinal…

SoftModel: A Neural Model That Grows Its Own Topology -- Governed Structural Growth for Continual In-Service Learning

arXiv:2608.16409v1 Announce Type: new Abstract: Today, a neural system is almost always used in two phases -- trained, then deployed -- and in that regime it freezes twice: training ends, and the topology itself was…

Learning Optimal Dynamic Matching via Graph Neural Networks

arXiv:2607.28925v2 Announce Type: replace Abstract: Dynamic matching markets require decisions about whom to match and when: matching now yields value but removes participants who may create better future opportunities.…

In-Context Learning to Assess Built Environment Impacts on Perceived Neighborhood Walkability Among Mobility-impaired Older Adults

arXiv:2608.14663v1 Announce Type: new Abstract: As global populations age, enhancing neighborhood walkability through inclusive urban design is important for mitigating built environment (BE) barriers that discourage…

Beyond Boundary Noise: Aggregated Aleatoric Uncertainty Fails to Capture Presence Ambiguity in 3D Lung Nodule Segmentation

arXiv:2608.14766v1 Announce Type: cross Abstract: Uncertainty estimation is critical for the safe clinical deployment of deep learning in medical image segmentation, with aleatoric uncertainty theoretically designed to…

How Many Samples Are Needed to Determine Causal Direction? Sharp Minimax Bounds for Bivariate LiNGAM

arXiv:2608.15840v1 Announce Type: cross Abstract: We study how many observations are needed to determine the causal direction between two linearly related variables. Classical LiNGAM theory shows that independent…

Supervising the Path to Fine Scales: GalerkinFlow for Scientific-Field and Image Super-Resolution

arXiv:2608.16546v1 Announce Type: cross Abstract: Most super-resolution models learn from paired data by supervising only the final high-resolution output. This provides little control over how the prediction should…

Last-Iterate Analyses of FTRL with the 1/2-Tsallis Entropy in Stochastic Bandits

arXiv:2510.22819v3 Announce Type: replace Abstract: The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it…

Memory-Bounded Continuation of Greedy Sampling for Continual Anomaly Detection

arXiv:2608.15277v1 Announce Type: cross Abstract: Greedy sampling produces a compact yet representative summary of normal data, which is essential for reliable anomaly detection that relies on measuring distance from…

CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?

arXiv:2608.16829v1 Announce Type: new Abstract: Video world models approximate the stochastic distribution of physical outcomes through generative sampling, but existing benchmarks score individual generations or…

Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads

arXiv:2601.21351v4 Announce Type: replace Abstract: Attentio-FFN disaggregation (AFD) is an emerging architecture for LLM decoding that separates state-heavy, KV-cache-dominated Attention computation from stateless,…

KOALA: Koopman Operator Learning for WiFi-Based Anticipatory Hum

arXiv:2608.15815v1 Announce Type: new Abstract: WiFi Channel State Information (CSI) has emerged as a privacy-preserving alternative to cameras for human pose estimation. However, existing approaches treat pose…

ReliaGate: Reliability Routing for Low-Stakes Wearable Stress Prediction

arXiv:2608.15951v1 Announce Type: new Abstract: We study when a wearable stress system should surface a prediction rather than change it. In low-stakes reflection and summary settings, aggregate accuracy is insufficient…

Efficient Safety Alignment of Language Models via Latent Personality Traits

arXiv:2607.07918v2 Announce Type: replace Abstract: Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives. Latent Adversarial…

Beyond Binary Priorities: Multi-Tier SLA Scheduling for Large Language Model Serving

arXiv:2608.16336v1 Announce Type: cross Abstract: Modern LLM serving deployments must simultaneously satisfy heterogeneous service-level objectives (SLOs) across a diverse population of user tiers, ranging from…

Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment

arXiv:2608.15693v1 Announce Type: cross Abstract: Running large AI models on resource-constrained edge devices requires model compression to reduce model size and computation. What compresses well, however, need not…

Distribution-free false-alarm calibration and chance-corrected spatial evaluation for industrial anomaly detection

arXiv:2608.15090v1 Announce Type: cross Abstract: Studies of industrial visual inspection commonly report the area under the receiver operating characteristic curve (AUROC) and the overlap between anomaly maps and…

Coverage-Maximizing Multinomial Subset Routing under Operational Constraints

arXiv:2608.16375v1 Announce Type: new Abstract: We introduce Multinomial Subset Routing (MSR), a new online routing framework over $K$ experts in which the learner keeps a multinomial routing policy instead of a…

Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference

arXiv:2608.15383v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models reduce arithmetic by activating only a small subset of experts per token, yet deployment still requires storing and moving…

The Distributional View of Knowledge Distillation

arXiv:2608.15215v1 Announce Type: cross Abstract: Token-level knowledge distillation (KD) matches two conditional distributions per position, yet the standard objectives compare them pointwise: a Kullback-Leibler…

Cross-Entropy Risk Estimation for Language Models: Inconsistency Must Be Dense, and the Holdout Method Is No Exception

arXiv:2608.15798v1 Announce Type: new Abstract: Language models are compared by their held-out per-token cross-entropy risk---the quantity scaling laws are fitted to. We show that it cannot be consistently estimated.…

Lipschitz Bandits with Arbitrary Feedback Delays

arXiv:2608.15036v1 Announce Type: new Abstract: The Lipschitz bandit problem extends the traditional multi-armed bandit framework to continuous action spaces by assuming that the reward functions satisfy a Lipschitz…

LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review

arXiv:2608.14626v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved substantial progress in safety alignment, yet their safety guarantees remain significantly weaker in low-resource and…

ARISE: An adaptive residual-informed stability ensemble for feature selection in small-sample biomedical omics

arXiv:2608.14866v1 Announce Type: cross Abstract: Objective: Small-sample molecular classification requires feature selectors that identify predictive, stable, and nonredundant subsets for binary and multiclass…

A Physics-Informed Hybrid Neural Operator for Transient Magnetization Prediction in Power Magnetics

arXiv:2608.02965v2 Announce Type: replace Abstract: Magnetic components in high-frequency, high-power-density converters are increasingly driven by non-sinusoidal flux-density waveforms with fast transitions, minor-loop…

SAGA: Structure-Attended Generative Action Embedding Model that encodes Multi-Surface User Action Sequences

arXiv:2608.15429v1 Announce Type: new Abstract: Prior embedding models for sequential recommendation typically operate within a homogeneous action space, limiting their ability to capture cross-surface behavioral…

Routing Divergence Is Not Evidence of Behavioral Influence in Same-Weight MoE Self-Distillation

arXiv:2608.15787v1 Announce Type: new Abstract: Two Mixture-of-Experts (MoE) forward passes can share every weight yet route the same token through different experts. This creates a possible blind spot in same-weight…

Optimizing Multi-Market Participation of Battery and Electrolyser Systems Based on Field Performance

arXiv:2608.16238v1 Announce Type: new Abstract: The increasing share of renewable energy in power systems creates a need for fast-response and flexible resources to maintain system stability. With the expansion of…

ClawGym II: Exploring Black-Box RL on Agent Harness

arXiv:2608.16798v1 Announce Type: cross Abstract: Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning…

Measuring the Prevalence of Policy Violating Content with ML Assisted Sampling and LLM Labeling

arXiv:2602.18518v2 Announce Type: replace Abstract: Content safety teams need metrics that reflect what users actually experience, not only what is reported. We study prevalence: the fraction of user views (impressions)…

When Single-Dataset Conclusions Fail: A 45-Task Study of Threshold Tuning and Resampling for Imbalanced Classification

arXiv:2608.16147v1 Announce Type: cross Abstract: Class-imbalance handling is routinely evaluated on a single benchmark dataset, and the resulting conclusions are reported as if they were properties of the method. We…

Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks

arXiv:2608.14823v1 Announce Type: new Abstract: Are heterophilic nodes in a graph harder to classify because they are heterophilic or because they are rare? Some existing work frames classification of such nodes as a…

PL-Guard: Probabilistic Logic Reasoning for LLM Guardrails

arXiv:2608.15673v1 Announce Type: new Abstract: Large language model guardrails can be viewed as policy-consistency problems: a system must determine which policy-relevant facts hold in a prompt-response pair and what…

Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning

arXiv:2608.15869v1 Announce Type: cross Abstract: Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments. By generating…

Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning

arXiv:2608.14851v1 Announce Type: cross Abstract: Learning and skill mastery require extensive and deliberate practice. In many learning settings, producing high-quality pedagogical materials can require a high level of…

EMASAM: a Computationally Efficient Sharpness-Aware Minimization via EMA-Guided Perturbations

arXiv:2608.15105v1 Announce Type: new Abstract: Recent progress in optimization research has highlighted the sharpness of the loss landscape as a key factor in narrowing the generalization gap. Motivated by this…

Improving the matrix multiplication exponent with modern optimization and AlphaEvolve

arXiv:2608.16884v1 Announce Type: cross Abstract: The current best bounds on the matrix multiplication exponent $\omega$ are obtained through a refinement of the laser method called combination loss analysis (Duan et…

Turning spectra into images improves plant trait retrieval with 2D-CNNs

arXiv:2608.16661v1 Announce Type: cross Abstract: Hyperspectral reflectance spectroscopy enables non-destructive estimation of plant functional traits, yet current deep learning approaches process spectra as…

Second-Moment Memory in Coordinatewise Adam

arXiv:2608.15824v1 Announce Type: new Abstract: Adam retains a moving average of past squared gradients in its denominator, but the optimization cost of this memory is not well understood. We show that second-moment…

Decentralized Federated Learning by Partial Message Exchange

arXiv:2603.01730v4 Announce Type: replace Abstract: Decentralized federated learning (DFL) has emerged as a transformative server-free paradigm that enables collaborative learning over large-scale heterogeneous…

AutoSR: Automatic Symbolic Regression by Searching Research States

arXiv:2608.16876v1 Announce Type: cross Abstract: We introduce Automatic Symbolic Regression (AutoSR), a fully automated system that instantiates Research-Space Symbolic Regression by searching persistent scientific…

Random Quadratic Form with random forcing: Metastable synchronization by noise

arXiv:2608.16664v1 Announce Type: cross Abstract: We study the Random Quadratic Form (RQF) on a sphere in the presence of random Brownian forcing. We show that the forcing does not effectively change the law of the…

Quantum Large Language Models via Tensor Network Disentanglers

arXiv:2410.17397v2 Announce Type: replace-cross Abstract: We introduce a framework for seamlessly integrating quantum computing into pretrained large language models (LLMs). The key idea is to construct a hybrid…

Developing an Offshore Machine Learning Surface Layer Scheme

arXiv:2608.14935v1 Announce Type: cross Abstract: Turbulent fluxes between the surface and the atmosphere are typically parameterized using empirically fit relationships. Here we test machine learning techniques for…

Crystal-structure design by agentic AI in a language of motifs

arXiv:2608.15900v1 Announce Type: cross Abstract: Data-driven materials discovery interpolates more reliably than it extrapolates and seldom reaches new structure types. We present MatEvolve, an agentic-AI framework…

Forward Pass Domain Adaptation (Without Cross-Layer Backpropagation)

arXiv:2608.14563v1 Announce Type: new Abstract: Forward-Pass-Only MLP training (FPO) adapts large language models without a backward pass through the model body, achieving 2.7--3.2x the throughput of standard…

RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models

arXiv:2605.26632v3 Announce Type: replace Abstract: Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via…

RetroMPA: A Molecular Property-Aware Auxiliary Framework for Enhancing Retrosynthesis Prediction

arXiv:2608.16111v1 Announce Type: new Abstract: Retrosynthesis is a cornerstone of drug discovery and organic synthesis. While data-driven deep learning models have shown remarkable progress, they autonomously learn…

Non-Crossing Deep Quantile Regression for Distributional Survival Prediction

arXiv:2608.16864v1 Announce Type: cross Abstract: In survival analysis the way covariates act on the risk of an event often differs between early and late failure times, yet hazard- and mean-based summaries collapse…

Sparse Prototype Code Underlies Classification and Prediction Across Modalities

arXiv:2608.15632v1 Announce Type: new Abstract: Neural representations have become a central tool for studying the internal mechanisms of modern AI models, yet their complex high-dimensional structure makes them…

Explainability Boosted Anomaly Detection Framework for O-RAN based NextG Networks

arXiv:2608.14826v1 Announce Type: cross Abstract: The wireless networks have historically faced significant security vulnerabilities, necessitating advanced anomaly detection mechanisms, especially as networks evolve…

Metaplasticity as adaptive gradient preconditioning for incremental learning

arXiv:2608.14634v1 Announce Type: new Abstract: Biological intelligence naturally prevents catastrophic forgetting through Complementary Learning Systems (CLS) theory, a macroscopic consolidation process driven at the…

JAPE: Joint Anomaly Prediction and Intrinsic Explanation in Multivariate Time Series

arXiv:2608.11801v2 Announce Type: replace Abstract: Multivariate time-series anomaly prediction aims to identify whether and when anomalies will occur over a future horizon from historical observations. Existing methods…

Generative Learning of Separatrices

arXiv:2608.14743v1 Announce Type: new Abstract: The identification and reconstruction of the boundaries separating basins of attraction in multistable, multidimensional dynamical systems presents a fundamental challenge…

Iso-Riemannian Optimization on Learned Data Manifolds

arXiv:2510.21033v3 Announce Type: replace-cross Abstract: We develop a theory of iso-Riemannian optimization for problems constrained to learned data manifolds, a setting in which classical Riemannian optimization - and…

Representation Is Not Enough: Body-Localized Thermal Evidence for Contactless Stress and Craving Sensing in Opioid Use Disorder

arXiv:2608.16087v1 Announce Type: cross Abstract: Removing wearables from physiological monitoring also removes their supervision: the signal indicating where and when a stress response occurred. Contactless stress…

pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier

arXiv:2608.14658v1 Announce Type: new Abstract: We introduce pico-type, a byte-level multi-head content classifier with approximately 1.5 million parameters that simultaneously predicts seven content properties from raw…

The Physical Cutoff Does Not Restore Homogenization: Phase-Dependent Burning in the Strain G-Equation

arXiv:2608.15337v1 Announce Type: cross Abstract: We disprove the expectation stated by Xin, Yu, and Ronney that the physical positive part strain $G$-equation should possess an effective burning velocity in cellular…

A 2-Block Architecture for Real-Time EEG Gait Decoding: A Pilot Study

arXiv:2608.02083v2 Announce Type: replace Abstract: Closed-loop lower-limb exoskeleton control via Electroencephalography (EEG) remains limited by motion artifacts, low signal-to-noise ratio, and binary gait…

When do machine-learned exchange-correlation improvements inherit into density-functional tight binding?

arXiv:2608.14875v1 Announce Type: cross Abstract: Machine-learned exchange-correlation functionals correct band gaps at near-semilocal cost, while density-functional tight binding reaches the $10^3$-$10^6$-atom regime;…

Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization

arXiv:2602.09761v2 Announce Type: replace Abstract: In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic…

No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage

arXiv:2608.15286v1 Announce Type: new Abstract: We introduce AgentRelBench, an environment-agnostic reliability instrument that computes ground-truth, severity-priced damage from database state diffs across repeated…

Helios 2.0: A Robust, Ultra-Low Power Gesture Recognition System Optimised for Event-Sensor based Wearables

arXiv:2503.07825v3 Announce Type: replace-cross Abstract: We present an advance in wearable technology: a mobile-optimized, real-time, ultra-low-power event camera system that enables natural hand gesture control for…

Robust Privacy: Inference-Stage Privacy through Certified Robustness

arXiv:2601.17360v3 Announce Type: replace Abstract: An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives of the model's training…

ETHOS: Towards a Modular Ethics Framework for Clinical Multi-Agent Systems

arXiv:2608.15424v1 Announce Type: cross Abstract: The rapid adoption of large language models has enabled the development of clinical multi-agent systems (MAS) capable of integrating multimodal patient data and…

Sequential Batch Learning in Finite-Action Linear Contextual Bandits

arXiv:2004.06321v2 Announce Type: replace Abstract: We study the sequential batch learning problem in linear contextual bandits with finite action sets, where the decision maker is constrained to split incoming…

Deep learning-based computed tomography (CT) derived body composition classifier for colorectal cancer patients

arXiv:2608.15712v1 Announce Type: cross Abstract: Background: Accurate body composition analysis using Computed Tomography (CT) scans is essential for assessing skeletal muscle area (SMA) and skeletal muscle density…

Wiring Beats Blending: What Transfers Between Transformer Sizes -- and What Doesn't

arXiv:2608.02829v3 Announce Type: replace Abstract: Model families are typically trained size by size, each from scratch. Can a pretrained large model instead be converted into a smaller sibling? We characterize the…

Leveraging Machine Unlearning for Cost-Efficient Preference Alignment

arXiv:2504.06659v2 Announce Type: replace Abstract: Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like reinforcement learning with human feedback face notable…

Resource-Efficient QUBO Formulation for Anchored Currency Arbitrage

arXiv:2608.15889v1 Announce Type: cross Abstract: Currency arbitrage (CA) involves trading currencies in cycles to exploit discrepancies in market valuations. Quadratic unconstrained binary optimization (QUBO) involves…

Phase-Aware CNN for Real-Time 5G/6G Channel Estimation with Hardware-in-the-loop Validation

arXiv:2608.14676v1 Announce Type: cross Abstract: In 5G/6G wireless systems, accurate and timely channel estimation is critical to ensure reliable communication under complex, fast-changing radio conditions. This work…

Q-based Variational Inverse Reinforcement Learning

arXiv:2608.16888v1 Announce Type: new Abstract: The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences. However, explicitly specifying these preferences by…

Does the Heart Show Your Pain? Tackling the X-ITE Pain Challenge with Self-Supervised ECG Representation Learning

arXiv:2608.14662v1 Announce Type: cross Abstract: Accurate recognition of pain using physiological signals remains a challenging problem due to pain's subjective nature and high inter-individual variability. In this…

Optimal Watermark Localization in Mixed-Source Large Language Model Texts

arXiv:2608.14906v1 Announce Type: cross Abstract: Watermarking provides a principled way to authenticate text generated by large language models (LLMs). In practice, however, the final text may be mixed-source, with…

When Does the Best Sampling Temperature Rise with the Budget? Sufficient Conditions for Pass@k

arXiv:2608.14665v1 Announce Type: new Abstract: The temperature that maximizes pass@$k$ is often low for a small sampling budget and higher for a large budget. This pattern has been reported from Codex through recent…

Deep Analog: Open-Set Film Emulation with Reference-Conditioned 3D LUTs

arXiv:2608.14702v1 Announce Type: cross Abstract: Film emulation reproduces the look of an analog film stock on a new digital photograph. We target its open-set form -- matching any reference film frame from a single…

Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift

arXiv:2608.15037v1 Announce Type: cross Abstract: Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time…

PandasCorpus: A Resource of Real-World Pandas Workflows and Usage Patterns

arXiv:2608.14742v1 Announce Type: cross Abstract: Pandas has emerged as the de facto library for data processing and machine learning, widely used for tasks, such as data loading, transformation, and analysis. Despite…

Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games?

arXiv:2608.14982v1 Announce Type: new Abstract: Transformers applied to spatial imperfect-information games must represent map geometry while tracking hidden entities through time. We ask whether geometry-aware…

RagGAD: Rationale-Aware Conditional Gaussian Mixture Normalizing Flow for Unsupervised Graph Anomaly Detection

arXiv:2608.16018v1 Announce Type: new Abstract: Graph anomaly detection aims to identify nodes that deviate from normal behavioral patterns within graphs. However, existing methods largely rely on the homophily…

FedImp: Enhancing Federated Learning Convergence with Impurity-Based Weighting

arXiv:2608.14654v1 Announce Type: new Abstract: Federated Learning (FL) is a collaborative paradigm that enables multiple devices to train a global model while preserving local data privacy. A major challenge in FL is…

CoM$^3$eT: A foundation model for medical image analysis through federated, multidimensional context integration

arXiv:2608.16268v1 Announce Type: cross Abstract: Medical foundation models improve generalization when training AI models with limited labeled data, but remain confined to a single specialty, such as pathology or…

The Ethical Decision Head: Operationalizing Normative Ethics in Autonomous Vehicles via Reinforcement Learning from Human Feedback

arXiv:2608.16710v1 Announce Type: new Abstract: As autonomous vehicles (AVs) approach Level 4 and Level 5 operational capability [SAE International, 2018], their on- board decision systems must handle not only…

A Probabilistic Circuit-Induced Pseudo-Metric for Out-of-Distribution Detection

arXiv:2608.09117v2 Announce Type: replace Abstract: Probabilistic Circuits (PCs) are tractable generative models whose internal nodes encode a hierarchy of probabilistic summaries over different variable scopes.…

High-Dimensional Nonparametric Change-Point Detection via Low-Rank Degree-Three Density Projection

arXiv:2608.15466v1 Announce Type: new Abstract: Distributional changes can be invisible to means and covariances yet appear in skewness, asymmetric interactions, or other third-order structure. We develop a…

When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation

arXiv:2608.14659v1 Announce Type: cross Abstract: Large language models for code generation often produce incorrect solutions without reliable indicators of failure. We study whether uncertainty estimation methods…

Explainable Heterogeneous Anomaly Detection in Financial Networks via Adaptive Expert Routing

arXiv:2510.17088v3 Announce Type: replace Abstract: Financial anomalies arise from heterogeneous mechanisms - price shocks, liquidity freezes, contagion cascades, and momentum reversals - yet existing detectors produce…

SchurQuant: Groupwise Discrete Optimization for Layer-Wise LLM Quantization

arXiv:2608.15567v1 Announce Type: new Abstract: Weight-only post-training quantization (PTQ) enables the deployment of large language models under tight memory budgets, but accuracy often collapses at 2-3 bits. Existing…

Randomly initialized autoencoders: fixed points and edge-of-chaos

arXiv:2608.14638v1 Announce Type: new Abstract: In this paper we study autoencoders, a special class of deep neural nets (DNNs) whose performance can be characterized via their fixed points. This perspective naturally…

Variational Outlier-Robust Gaussian Process Regression with Generative Modeling

arXiv:2608.16606v1 Announce Type: new Abstract: Outliers can substantially distort Gaussian process regression (GPR) due to its conventional Gaussian observation likelihood, leading to inaccurate model learning and…

T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework

arXiv:2608.14953v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have opened opportunities to apply high-level code transformations to the field of code optimization, and it has since…

Large Language Models as Implicit Sociological Models: Reconstructing Voting Behaviour from Sociodemographic Profiles

arXiv:2608.15871v1 Announce Type: cross Abstract: Large language models (LLMs) trained on large-scale internet corpora encode extensive statistical regularities about social identities, attitudes, and political…

Asymptotics-guided learning and symbolic regression for dispersive resonances

arXiv:2608.16152v1 Announce Type: cross Abstract: We study resonance prediction in dispersive media, formulated as nonlinear spectral problems for volume integral operators. The main idea is to use asymptotic analysis…

Continuous Quantum Feedback Control via Kraus-Parameterized Belief Reinforcement Learning

arXiv:2608.15715v1 Announce Type: cross Abstract: Quantum feedback control requires acting on noisy continuous measurement records without direct access to the underlying quantum state. We propose Kraus-Parameterized…

BDIP-Net: Dual-Interaction Graph Learning for Property Prediction of Bilayer Materials

arXiv:2608.14640v1 Announce Type: new Abstract: Stacked bilayer materials exhibit rich stacking-dependent properties driven by the interplay between strong intra-layer bonding and weak inter-layer van der Waals…

Learning reshapes power-law anisotropy in internal representations

arXiv:2608.15239v1 Announce Type: new Abstract: Power-law anisotropy in internal representations has been observed across a wide range of biological and artificial neural systems, from state-of-the-art language models…

Earth Observation Foundation Models for Terrestrial Ecohydrology: From Representation Learning to Process Inference

arXiv:2608.15282v1 Announce Type: new Abstract: Earth observation foundation models (EOFMs) are emerging as reusable representation frameworks for data-driven retrieval, prediction and process modelling within…

Unraveling the Size Determination Mechanism of Nanocrystal Synthesis via Interpretable Neural Networks

arXiv:2608.14734v1 Announce Type: new Abstract: Deep learning models of nanocrystal synthesis enable the prediction of size and shape by encoding precursors and reaction conditions. However, their black-box nature…

MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocation

arXiv:2608.15299v1 Announce Type: new Abstract: Sparsely-activated Mixture-of-Experts (MoE) Transformers universally fix the same number of routed experts across all layers, a convention that ignores the well-documented…

Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification?

arXiv:2608.15365v1 Announce Type: new Abstract: Regret minimization (RM) and best-arm identification (BAI) are two fundamental objectives in multi-armed bandits. Among regret-minimizing algorithms, $1/2$-Tsallis-INF is…

MDP Planning as Policy Inference

arXiv:2602.17375v3 Announce Type: replace Abstract: We formulate episodic Markov decision process (MDP) planning as Bayesian inference over policies. The primary contribution is conceptual: the policy itself is treated…

Projection-based multifidelity linear regression for data-scarce applications

arXiv:2508.08517v2 Announce Type: replace-cross Abstract: Surrogate modeling for systems with high-dimensional quantities of interest remains challenging, particularly when training data are costly to acquire. This work…

PLeDO: Pain Level Detection for Osteoarthritis from EMR Data

arXiv:2608.15719v1 Announce Type: cross Abstract: Osteoarthritis (OA) is a progressive chronic joint disease resulting in a breakdown of articular cartilage and bone when damaged joint tissues are not able to normally…

A Reproducibility Study of Partial Residual Ablations in Pre-LN Transformers

arXiv:2608.14689v1 Announce Type: new Abstract: Residual connections are a fundamental component of transformer architectures, yet the roles of the attention and feed-forward residual pathways remain poorly understood…

Beyond Field Accuracy: Two-Axis Diagnosis of Inverse-PINN Parameter Error

arXiv:2608.15373v1 Announce Type: new Abstract: Inverse physics-informed neural networks (PINNs) can reconstruct a field accurately while returning an incorrect physical parameter. We introduce a two-axis post-training…

Inferential Evaluation of Surrogate-Derived Models under Covariate Shift

arXiv:2608.15783v1 Announce Type: cross Abstract: In transfer-learning settings, a model derived from abundant surrogate labels may be deployed in a target population where gold-standard outcomes are unobserved.…

Calibrated Trust, Not Sharper Prediction: An Empirical Test of Uncertainty Fusion

arXiv:2608.14617v1 Announce Type: new Abstract: A recurring proposal in legal AI is to improve case-outcome prediction by fusing uncertainty tools (evidence graphs with belief propagation, sequential Bayesian odds…

$S^3$: A Smooth Simulation Surrogate for Optimizing Discrete Abstractions of Dynamical Systems

arXiv:2608.15920v1 Announce Type: cross Abstract: Intelligent systems are increasingly deployed in safety-critical settings with black-box controllers, including neural networks. The properties and behaviors of these…

What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models

arXiv:2608.14819v1 Announce Type: cross Abstract: Music foundation models are commonly used as frozen audio feature extractors, yet selecting which layer to extract from remains largely heuristic. Current practice…

Toward Optimal Second-Order Path-Length Guarantee for Adversarial Multi-Armed Bandits

arXiv:2608.15996v1 Announce Type: new Abstract: We study second-order path-length regret in adversarial $K$-armed bandits against oblivious loss sequences. Bubeck et al. [2019] designed an algorithm that achieves…

LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks

arXiv:2608.14927v1 Announce Type: cross Abstract: Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collaboration is worth its…

SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation

arXiv:2608.04419v2 Announce Type: replace Abstract: On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but standard reverse-KL training can assign insufficient probability…

A Low-Cost IoT Device for Environmental Monitoring and Embedded Solar Forecasting with On-Device Incremental Learning

arXiv:2608.14698v1 Announce Type: cross Abstract: Hyperlocal meteorological sensing is essential for accurate solar photovoltaic forecasting, yet professional-grade meteorological stations require investments easily…

Iterative Refinement Diffusion for Super-Resolved Data Assimilation of Multiscale Physical Systems

arXiv:2608.14744v1 Announce Type: new Abstract: Recovering high-resolution states from sparse, low-resolution observations is a central challenge in scientific machine learning and data assimilation. Classical data…

POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment

arXiv:2608.16407v1 Announce Type: cross Abstract: Point-of-interest (POI) recommendation models based on graph neural networks achieve strong performance by propagating collaborative signals over user-item interactions,…

Improved Regret Analysis for Parallel Gaussian Process Bandit Optimization

arXiv:2608.16492v1 Announce Type: cross Abstract: This paper studies the regret analysis for parallel Gaussian process (GP) bandit optimization. The known regret upper bounds for the widely used GP batched upper…

Hoeffding adaptive splitting trees for data stream classification with concept drift and ensemble learning

arXiv:2608.16659v1 Announce Type: new Abstract: Ensembles of decision trees are well-established methods for data stream classification. In ensemble learning, Hoeffding Trees are widely adopted as base learners,…

Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values

arXiv:2607.14345v4 Announce Type: replace Abstract: People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they…

The canonical facets of multi-separator polytopes

arXiv:2608.16861v1 Announce Type: cross Abstract: We initiate a polyhedral study of the graph multi-separator problem proposed by Irmai et al. (2024) as an alternative to the lifted multicut problem for application to…

Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR

arXiv:2605.02909v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs). While…

Experimentally Extending Quantum Kernel Learning to Quantum Data by NMR

arXiv:2412.09557v3 Announce Type: replace-cross Abstract: Quantum kernel learning (QKL) promises efficient machine learning by encoding feature maps onto exponentially large Hilbert spaces inherent in quantum systems.…

Online Convex Optimization with Dueling Feedback

arXiv:2608.15050v1 Announce Type: new Abstract: We study online convex optimization with dueling (pairwise comparison) feedback, where the learner observes only a binary preference between two queried points. While…

Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation

arXiv:2502.13207v4 Announce Type: replace-cross Abstract: Despite the increasing use of large language models for creative tasks, their outputs often lack diversity. Common solutions, such as sampling at higher…

AsyTO: Asymmetric Temporal Operator for Parameter-Efficient Multivariate Time Series Forecasting

arXiv:2608.16098v1 Announce Type: new Abstract: Multivariate time-series forecasting faces a structural dilemma: sharing one temporal predictor across variables is parameter-efficient but forces heterogeneous variables…

From Monte Carlo to neural networks approximations of boundary value problems

arXiv:2209.01432v4 Announce Type: replace-cross Abstract: In this paper we study probabilistic and neural network approximations for solutions to Poisson equation subject to Holder data in general bounded domains of…

BRAID: Learning Equilibrium Maps in Interdependent Security Games via Weight-Tied Iterative Graph Neural Networks

arXiv:2608.14856v1 Announce Type: cross Abstract: Computing Nash equilibria in interdependent security (IDS) games on networks is computationally expensive: best-response dynamics may need hundreds of iterations per…

MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment

arXiv:2608.14828v1 Announce Type: cross Abstract: Aligning a language agent to several objectives at once is a persistent failure mode of preference-based training: when objectives are combined additively, optimization…

A Novel Fourier Feature Network for Solving Partial Differential Equations

arXiv:2608.14733v1 Announce Type: new Abstract: Building on the foundation of single-hidden-layer neural networks, Fourier Feature Networks (FENs) are proposed, which incorporate Fourier features using $\cos$, $\sin$,…

LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights

arXiv:2602.17510v2 Announce Type: replace Abstract: We introduce LoRA-CRAFT (\textbf{C}ross-layer \textbf{R}ank \textbf{A}daptation via \textbf{F}rozen \textbf{T}ucker), abbreviated CRAFT throughout, an extremely…

Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluation

arXiv:2608.16482v1 Announce Type: cross Abstract: The dosing of intravenous fluids and vasopressors in sepsis is a sequential decision made under uncertainty and guided largely by clinical judgment, which makes it a…

Local Gains and Fixed-Assignment Set Losses in Shared Set Decoders

arXiv:2608.14717v1 Announce Type: cross Abstract: A query-relation deletion can improve the edited slot while reducing the utility of the prediction set that contains it. We study this tension in two related ResNet-50…

Identifying parameter couplings and uncertainties of mixed-noise stochastic systems via full-covariance Gaussian mixture network

arXiv:2608.15198v1 Announce Type: cross Abstract: Parameter identification of stochastic dynamical systems driven by mixed noises is challenging due to intractable likelihood functions. We propose PENN-GMD, a parameter…

Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer

arXiv:2608.15690v1 Announce Type: cross Abstract: Text-to-audio-video (T2AV) generation models produce a video and its soundtrack from a textual description, but offer no control over whose voice speaks in the output.…

GATTA: Graph Active Learning with Test-Time Augmentation

arXiv:2608.15084v1 Announce Type: new Abstract: Test-time augmentation (TTA) has proven effective for improving model robustness and uncertainty estimation in computer vision, yet its application to graph-structured…

Quantum Models with Multi-Stage Training for Compositional Concept Generalization

arXiv:2608.15601v1 Announce Type: new Abstract: Compositional Concept Generalization (CoCoGen), the ability to systematically recombine learned primitives in novel contexts, is a key challenge for multimodal learning.…

Belayer: Efficient Fault Tolerance for LLM Agentic RL Training

arXiv:2608.14635v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly trained with reinforcement learning in long-horizon, sandboxed environments. Unlike conventional RL, agentic RL…

Anatomy of a Quantized Agent: VRAM Stability and Forecasting in Code-Synthesis Agentic Workloads

arXiv:2608.15117v1 Announce Type: cross Abstract: Analytical models of peak VRAM consumption for LLM inference decompose memory into weight-storage, KV-cache, and activation terms parameterized by step count, tool…

Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols

arXiv:2507.19894v2 Announce Type: replace Abstract: With the rapid advancement of generative models, privacy, copyright, safety, and reliability risks have attracted growing attention. To mitigate these risks, machine…

Generalized Linear Bandits with Memory

arXiv:2608.15848v1 Announce Type: cross Abstract: We study generalized linear bandits with memory, an endogenous non-stationary setting in which rewards depend on past actions through a finite memory matrix. Building on…

Hybrid quantum recurrent neural network for remaining useful life prediction of turbofan engines

arXiv:2504.20823v3 Announce Type: replace Abstract: Accurate remaining useful life (RUL) estimation underpins safe operation and cost-effective maintenance of aerospace propulsion systems. We propose a Hybrid Quantum…

Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade

arXiv:2608.14650v1 Announce Type: new Abstract: Existing adaptive-inference and world-action-model systems use cheap-stage outputs or predicted futures to allocate additional computation. We study a narrower question:…

Automating Learner Assessment: Benchmarking Machine Learning and Deep Learning Models for EEG-Based Familiarity Prediction

arXiv:2608.16541v1 Announce Type: cross Abstract: Objective assessment of learning remains a fundamental challenge in education. Electroencephalography (EEG) provides a direct, non-invasive window into the neural…

Wolff-Parkinson-White Detection at 471:1 Class Imbalance: A Leakage-Controlled Study of the Data Bottleneck

arXiv:2608.14633v1 Announce Type: cross Abstract: Wolff-Parkinson-White (WPW) syndrome is a congenital cardiac pre-excitation, clinically important and often missed on the resting 12-lead ECG. Detection is hard: the…

Operator-Theoretic Generalization Bounds for Multitask Deep Learning

arXiv:2608.15982v1 Announce Type: new Abstract: We develop operator-theoretic generalization bounds for deep multi-output function classes by representing network layers as Koopman composition operators on vector-valued…

Score Attack: A Lower Bound Technique for Optimal Differentially Private Learning

arXiv:2303.07152v3 Announce Type: replace-cross Abstract: Achieving optimal statistical performance while ensuring the privacy of personal data is a challenging yet crucial objective in modern data analysis. However,…

Layers Matter: Why Continual Learning Regularization Should Be Layer-Adaptive

arXiv:2608.15901v1 Announce Type: new Abstract: Continual learning regularizers like EWC fight forgetting by penalizing changes from previous-task parameters with per-parameter importance, typically diagonal Fisher…

Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments

arXiv:2608.16747v1 Announce Type: new Abstract: Many areas of AI research, such as language model interpretability and chain of thought faithfulness, seek to explain model behaviors. But what constitutes a "good"…

Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking

arXiv:2608.14808v1 Announce Type: cross Abstract: When a user question is underspecified, a capable model should recognize that its context is insufficient, identify the missing information, ask for it, and respond only…

Geometry of Forgetting: Representation Flux in Continual Learning

arXiv:2608.15854v1 Announce Type: new Abstract: Catastrophic forgetting remains a fundamental obstacle to continual learning, where neural networks lose previously acquired knowledge while learning new tasks. Existing…

Architecture-Dependent Causal Transfer of Activation States Across Large Language Models

arXiv:2608.16347v1 Announce Type: cross Abstract: Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and latency. We ask…

Efficient Coreset Selection via K-Nearest Neighbor Graphs

arXiv:2608.16270v1 Announce Type: new Abstract: Coreset selection reduces the cost of model training by replacing a large training set with a small representative subset. Existing gradient-approximation coreset methods…

Machine Learning Approaches to Decoding Topological Quantum Codes

arXiv:2608.15760v1 Announce Type: cross Abstract: Decoding is an essential component of quantum error correction (QEC), translating stabilizer measurement outcomes into corrective actions that suppress logical errors…

Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach

arXiv:2608.15224v1 Announce Type: new Abstract: Reliable post-hoc evaluation asks whether already generated text satisfies a target criterion after generation. In this paper we study a focused frozen-embedding setting…

Learning to Bid with Unknown Private Values in Budget-Constrained First-Price Auctions

arXiv:2605.09448v2 Announce Type: replace Abstract: We study the operational problem of automated bidding in repeated first-price auctions under budget and return-on-spend (RoS) constraints. In this setting, an…

Evaluating the trustworthiness of the Fr\'echet Inception Distance with stochastic embedding representations

arXiv:2601.21979v2 Announce Type: replace Abstract: Feature embeddings acquired from pretrained models are widely used in medical applications of deep learning to assess the characteristics of datasets; e.g. to…

PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection

arXiv:2608.15802v1 Announce Type: cross Abstract: Out-of-distribution (OOD) detection remains challenging for image classifiers, especially when near-OOD samples lie close to in-distribution (ID) class boundaries.…

A Unified Mamba--MoE Surrogate for Closed-Loop Simulation and Measurement-Window Forecasting of Inverter Transients

arXiv:2608.15051v1 Announce Type: new Abstract: This paper proposes a Mamba surrogate model with mixture-of-experts (MoE) routing to represent the transient dynamics of inverter-based resources. A Mamba surrogate model…

Feature-Aware (Hyper)graph Generation via Next-Scale Prediction

arXiv:2506.01467v4 Announce Type: replace Abstract: Graph generative models perform well on small-scale structured data but struggle to scale to large, complex structures. Hierarchical approaches improve scalability but…

PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data

arXiv:2608.16419v1 Announce Type: new Abstract: Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here we show that cellular…

Evaluating the impact of adversarial traffic patterns on vanet communication using veins simulation

arXiv:2608.14583v1 Announce Type: cross Abstract: Vehicular Ad Hoc Networks (VANETs) are a key component of intelligent transportation systems, enabling real-time communication between vehicles. However, their open and…

EMS Coreset: An Efficient Expectation-Maximization Algorithm for Sinkhorn Coreset

arXiv:2608.16101v1 Announce Type: cross Abstract: Coresets distill large datasets into small, representative subsets for efficient downstream learning. Yet Optimal Transport (OT)-based selection typically requires…

Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation

arXiv:2608.15949v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled their use as conversational recommender systems (CRS), demonstrating strong recommendation accuracy and…

DumpsterCluster: From Dumpster Diving to Serving LLaMA-70B on $60 GPUs

arXiv:2608.14614v1 Announce Type: new Abstract: As AI datacenters retire functional GPUs, vast quantities of still capable accelerators enter secondary markets. This paper investigates whether these retired GPUs can…

Contraction-Aware Reinforcement Learning for Nonlinear Control with Statistical Robustness

arXiv:2506.15700v2 Announce Type: replace Abstract: Control contraction metrics (CCMs)-defined by Riemannian metrics under which a closed-loop system is incrementally exponentially stable-offer a constructive framework…

Convolution Smoothed Quantile Regression for XGBoost

arXiv:2608.15290v1 Announce Type: cross Abstract: The increasing availability of large and complex datasets across many scientific disciplines has led to widespread adoption of machine learning (ML) for prediction.…

Self-Supervised Noise2Noise-Enhanced Denoising for Continuous-Scan Air-Plasma THz Spectroscopy

arXiv:2608.16454v1 Announce Type: cross Abstract: Terahertz time-domain spectroscopy (THz-TDS) based on air-plasma generation and balanced air-biased coherent detection offers gap-free broadband coverage, but individual…

Convex Optimization with Nested Evolving Feasible Sets

arXiv:2605.07386v2 Announce Type: replace Abstract: \emph{Convex Optimization with Nested Evolving Feasible Sets (CONES)} is considered where the objective function \(f\) remains fixed but the feasible region evolves…

On Stopping Rules and Spatial Adaptation for CART

arXiv:2608.15649v1 Announce Type: cross Abstract: The popular CART algorithm for regression trees combines a greedy splitting rule with a stopping rule, but while the splitting rule has been well studied, the…

Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges (Extended Version)

arXiv:2608.16050v1 Announce Type: cross Abstract: Spreadsheets are a primary medium for publishing tabular data, yet automatically extracting structured content from them remains difficult due to heterogeneous layouts,…

Towards Unified Approaches in Self-Supervised Event Stream Modeling: Progress and Prospects

arXiv:2502.04899v3 Announce Type: replace Abstract: The proliferation of digital interactions across diverse domains, such as healthcare, e-commerce, gaming, and finance, has resulted in the generation of vast volumes…

Data-Efficient and Interpretable Classification of Circulating Tumor Cell Phenotypes in Microfluidic Devices via Deep Learning

arXiv:2608.16870v1 Announce Type: new Abstract: Accurate classification of circulating tumor cell (CTC) phenotypes can provide valuable information for assessing metastatic potential. Label free microfluidic devices…

Decentralized Federated Learning for Heterogeneous Multi-Task Semantic Communication

arXiv:2608.15256v1 Announce Type: cross Abstract: Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL). However, pushing…

The Optimal Sample Complexity of Multiclass and List Learning

arXiv:2604.24749v3 Announce Type: replace Abstract: While the optimal sample complexity of binary classification in terms of the VC dimension is well-established, determining the optimal sample complexity of multiclass…

Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning

arXiv:2608.14963v1 Announce Type: new Abstract: Pareto Conditioned Networks learn multiple multi-objective reinforcement learning behaviours by conditioning a single policy on a desired return command. However, the…

On the Principles Behind Neural Network Optimizers

arXiv:2608.16760v1 Announce Type: new Abstract: Reliable optimization is central to neural network (NN) training, yet Adam, the default optimizer for modern LLMs, rests on a fragile foundation. This thesis develops a…

Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data

arXiv:2410.13341v4 Announce Type: replace Abstract: High quality annotations are increasingly a bottleneck in the explosively growing machine learning ecosystem. Scalable evaluation methods that avoid costly annotation…

Technological Advances in Detecting and Managing Cognitive Impairment in Older Adults: Trends, Challenges, and Future Directions

arXiv:2607.28687v2 Announce Type: replace Abstract: As populations age, cognitive decline from mild cognitive impairment (MCI) to dementia is a defining health challenge of the coming decades, yet routine assessment…

LiD-GLM: Lipschitz-constrained Deep Generalized Linear Models

arXiv:2608.16340v1 Announce Type: cross Abstract: The combination of traditional statistical models and neural network (NN) components into semi-structured hybrid models is an intriguing approach to construct models…

Demystifying Oversmoothing in Sheaf Neural Networks: An Index-Theoretic Criterion

arXiv:2608.16180v1 Announce Type: new Abstract: To combat oversmoothing in Graph Convolutional Networks, Sheaf Neural Networks (SNNs) were proposed as a generalization by equipping the graph with a sheaf structure and…

Degradation-Aligned Self-Supervised Learning for State of Health Estimation of Lithium-Ion Batteries under Label Sparsity

arXiv:2608.16612v1 Announce Type: cross Abstract: An accurate estimation of the state of health (SOH) underpins a safe and optimized use of the battery system. Although compelling, data-driven SOH estimation models…

SL-S4Wave: Self-Supervised Learning of Physiological Waveforms with Structured State Space Models

arXiv:2606.19888v2 Announce Type: replace Abstract: Modeling long-sequence medical time series data, such as electrocardiograms (ECG), poses significant challenges due to high sampling rates, multichannel signal…

CoupVisor: Strategy Optimization by Round and Challenge Decision Support

arXiv:2608.15868v1 Announce Type: cross Abstract: This paper presents CoupVisor, a decision-support system for the hidden-information card game Coup. It addresses two questions: what a player should do on each turn, and…

Not All Attention Is Equal: A Quantitative Survey of the EEI Trade-off

arXiv:2608.15459v1 Announce Type: new Abstract: Attention mechanisms have driven machine learning for a decade, from neural machine translation to language models that do general-purpose reasoning. This survey covers…

EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction

arXiv:2302.12177v4 Announce Type: replace-cross Abstract: Predicting the binding sites of target proteins plays a fundamental role in drug discovery. Most existing deep-learning methods consider a protein as a 3D image…

From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection

arXiv:2512.10485v3 Announce Type: replace-cross Abstract: Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains…

Free-Flow Class-Incremental Learning: Towards Robust CIL under Variable Class Arrivals

arXiv:2604.02765v2 Announce Type: replace Abstract: Class-incremental learning (CIL) is commonly evaluated under predefined schedules with fixed or nearly equal class increments, leaving irregular class-arrival…

The Quantum Shortcut: Complex Phase-State Dynamics Reduce the Optimization Steps of Sequence Models

arXiv:2608.14691v1 Announce Type: new Abstract: Sequence models are conventionally distinguished by their backbone, the mechanism that routes information across positions, such as attention or recurrence. This paper…

One Residual with Three Reuses: A Wristband Front End for Gesture Sensing

arXiv:2608.16542v1 Announce Type: new Abstract: Continuous wrist-worn hand sensing for gesture interfaces and motor symptom monitoring needs an always-on front end that fits inside a coin-cell power budget while pairing…

A Physiology-Informed Digital Twin Framework for Simulating Liver Health Progression

arXiv:2608.14969v1 Announce Type: new Abstract: We present a physiology-informed digital twin of the human liver designed for longitudinal simulation of liver function and early-stage disease progression. The model,…

Demo: Real-time Generative Multicasting with On-Device Intent-aware Semantic Decomposition

arXiv:2608.14600v1 Announce Type: cross Abstract: We present a demonstration for generative multicasting with on-device, intent-aware semantic decomposition. At the transmitter, DNN-based segmentation extracts a…

Toward Better Assessment of LLMs' Performance in Clinical Error Detection

arXiv:2608.16643v1 Announce Type: cross Abstract: Automated detection of errors in clinical documentation is a promising application of large language models (LLMs), yet decisions to deploy such models rest on…

Stitch the Fragments: One-Shot Hierarchical Federated Clustering

arXiv:2601.06404v2 Announce Type: replace Abstract: Federated Clustering (FC) faces a critical bottleneck in real-world scenarios, i.e., global clusters are rarely intact, often fragmenting into incomplete,…

Learning symplectic model reduction based on an approximation theorem of symplectic embeddings

arXiv:2606.04623v2 Announce Type: replace Abstract: High-dimensional Hamiltonian systems play a central role in many scientific and engineering disciplines, with dynamics that evolve on symplectic manifolds. Although…

A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing

arXiv:2607.16183v2 Announce Type: replace Abstract: To help address the escalating energy and latency demands of machine-learning workloads, we introduce a blueprint for an energy-efficient and fast thermodynamic…

OceanLight: Efficient Global Ocean Forecasting via Geometry-Adaptive Unstructured Mesh Representation

arXiv:2608.16070v1 Announce Type: new Abstract: Reliable global ocean forecasting is critical for climate monitoring, marine navigation, and extreme event early warning. Physics-based ocean forecasting models impose…

VirnyFlow: Optimizing ML Pipelines for Accuracy, Fairness, and Stability at Scale

arXiv:2506.01584v2 Announce Type: replace Abstract: Developing machine learning (ML) systems for real-world deployment requires navigating context-dependent trade-offs among accuracy, fairness, stability, and other…

Lightweight Deep Learning-Based Channel Estimation for RIS-Aided Extremely Large-Scale MIMO Systems on Resource-Limited Edge Devices

arXiv:2507.09627v3 Announce Type: replace-cross Abstract: Next-generation wireless technologies such as 6G aim to meet demanding requirements such as ultra-high data rates, low latency, and enhanced connectivity.…

Macroeconomic Forecasting with Large Language Models

arXiv:2407.00890v5 Announce Type: replace-cross Abstract: This paper presents a comparative analysis evaluating the accuracy of Large Language Models (LLMs) against traditional macro time series forecasting approaches.…

Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines

arXiv:2603.06952v2 Announce Type: replace Abstract: As graphs scale to billions of nodes and edges, graph Machine Learning workloads are constrained by the cost of multi-hop traversals over exponentially growing…

Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries

arXiv:2606.08410v2 Announce Type: replace Abstract: Personalized decision-making in multi-objective bandits requires learning user-specific trade-offs among competing objectives. Since arm utility depends on both…

Sufficient Dimesion Reduction via Generalized Stein's Lemma

arXiv:2608.15121v1 Announce Type: cross Abstract: Sufficient dimension reduction (SDR) seeks the minimal subspace of the predictors that captures the full conditional distribution of the response, which is known as the…

From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving

arXiv:2608.14771v1 Announce Type: cross Abstract: Making language models solve constraint problems reliably often means having them translate the problem into a formal specification and delegating the search to a sound…

Zero-Shot Instruction Following in RL via Structured LTL Representations

arXiv:2602.14344v2 Announce Type: replace Abstract: We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during training. In this setting,…

Learning Multi-Timescale Interventions under Safety and Resource Constraints

arXiv:2508.03875v4 Announce Type: replace Abstract: Many sequential decision problems offer qualitatively different ways of influencing the environment: some interventions act immediately, whereas others induce…

Behaviour Is an Incomplete Measure of Reasoning Development: Cross-surface pre-arrival accessibility and the limits of developmental inference in a recurrent-depth reasoner

arXiv:2608.16085v1 Announce Type: new Abstract: Capability development is routinely inferred from behavioural thresholds, from final checkpoints, or from what a decoder can read out of a hidden state. These quantities…

Evolving Executable Pipeline Programs for AutoML with Language Models

arXiv:2608.16416v1 Announce Type: new Abstract: Automated machine learning (AutoML) systems search for pipelines within a space of preprocessing operators, learners, and hyper-parameters specified in advance: they can…

FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy

arXiv:2608.15602v1 Announce Type: new Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of…

Early Cycle Charge Trajectory Generative Prediction and Full Life Cycle Health Management of Iron-Chromium Flow Batteries Based on FlowBD-E1

arXiv:2608.14637v1 Announce Type: new Abstract: Long-duration stationary energy storage requires batteries whose degradation can be detected before substantial capacity loss has accumulated. Iron-chromium redox flow…

SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation

arXiv:2608.14647v1 Announce Type: new Abstract: Dirty-history rollouts make multi-turn on-policy self-distillation (OPSD) brittle: once a student emits an erroneous intermediate reply, later turns are conditioned on…

Quantifying the Gap Between Laboratory Battery Test Patterns and Field Duty Profiles

arXiv:2608.16212v1 Announce Type: new Abstract: Laboratory battery tests provide the main empirical basis for battery performance and degradation studies, but their operating patterns do not directly represent field…

The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning

arXiv:2608.16245v1 Announce Type: new Abstract: Disentangled representation learning seeks latent representations whose indicidual dimensions each align with a distinct covariate. Unsupervised approaches typically…

Take it Personally: The Limits of General SSL Representations for Real-Life PPG Emotion Detection

arXiv:2608.14675v1 Announce Type: new Abstract: While Self-Supervised Learning (SSL) effectively extracts general representations from noisy, unconstrained physiological signals such as photoplethysmography (PPG), its…

TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity

arXiv:2608.15767v1 Announce Type: new Abstract: We introduce TinyCast, an attention-free zero-shot forecaster that emits a predictive distribution from 146,505 parameters, on the premise that at this size the periodic…

Hide&Seek: Learning to Explain in an End-to-End Differentiable Network

arXiv:2608.16689v1 Announce Type: cross Abstract: Instance-wise feature selection is a valuable tool for interpreting labeled data and the predictions of black-box models. In contrast to global feature selection…

GEO-Flag: Detecting and Measuring GEO-Optimized Web Content

arXiv:2608.16824v1 Announce Type: new Abstract: Generative Engine Optimization (GEO) modifies web content to increase its likelihood of being selected and cited by generative search engines. This can give strategically…

Learning to Price with Persuasion

arXiv:2608.16699v1 Announce Type: cross Abstract: Motivated by modern marketplaces, where the platform or the seller routinely gathers detailed user profiles, we study a novel learning theoretic model that…

Annealed Softmax Greedy in Many-Armed Bayesian Bandits

arXiv:2605.31034v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards and group-based policy optimization methods update a stochastic policy by sampling multiple completions per prompt and…

On Cross-Validation for Hyperparameter Optimization of Deep Learning Image Classifiers

arXiv:2608.14705v1 Announce Type: cross Abstract: Hyperparameter optimization (HPO) can materially affect the performance of deep learning (DL) image classifiers, but there is little empirical guidance on how to derive…

p-Spin Glass Network Efficient Single-Batch Continual Learning

arXiv:2608.14774v1 Announce Type: new Abstract: Modern sequence models heavily rely on massive memory footprints and large-batch stochastic optimization, barriers that restrict sample efficiency and continual learning.…

An automatic-differentiation framework for time-lapse electrical resistivity tomography inversion of hydrologic dynamics

arXiv:2608.14661v1 Announce Type: new Abstract: Time-lapse electrical resistivity tomography (TL-ERT) provides spatially distributed information on subsurface hydrologic changes. However, inversion of long monitoring…

The Note-Chord-Voice Framework: Structured Source Separation and Causal Inference for EV Charging Data

arXiv:2608.14756v1 Announce Type: cross Abstract: Real-world EV charging data exhibit three interlocking pathologies: hardware fragmentation (network timeouts and billing resets split sessions), physical violations…

Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task

arXiv:2608.14916v1 Announce Type: cross Abstract: AI-generated music detectors are commonly evaluated against original songs, but real-world uploads are often remixed, re-encoded, pitch-shifted, or otherwise edited.…

In-Context Source and Channel Coding

arXiv:2601.10267v2 Announce Type: replace Abstract: Separate Source-Channel Coding (SSCC) remains attractive for text transmission due to its modularity and compatibility with mature entropy coders and powerful channel…

Periodic Topological Deep Learning for Polymer Design and Discovery

arXiv:2605.26833v2 Announce Type: replace Abstract: Polymers underpin applications across energy, healthcare, and materials science, yet their vast chemical space makes systematic discovery challenging. Most machine…

FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting

arXiv:2608.15310v1 Announce Type: cross Abstract: Multimodal data collected by heterogeneous devices are used for collaborative training, where federated learning (FL) serves as a key paradigm for effective distributed…

Benchmarking Quantum Machine Learning for Power-System Attack Detection: Evaluation Choices Decide the Outcome Before the Models Do

arXiv:2608.15617v1 Announce Type: new Abstract: Machine-learning detectors for power-system cyberattacks are themselves attack surfaces, and quantum machine learning has been proposed for them. We benchmark…

Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors

arXiv:2608.15559v1 Announce Type: new Abstract: Anomaly detection in dynamic graphs underpins financial fraud analysis, intrusion detection, and platform integrity, where automated decisions require human-interpretable…

WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales

arXiv:2505.04608v5 Announce Type: replace Abstract: Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but…

Spectral Certificates and Projection-DPP Rounding for Determinantal MAP Selection

arXiv:2606.19411v3 Announce Type: replace Abstract: Selecting a fixed-size subset that maximizes the determinant of a positive semidefinite kernel is the MAP problem for a size-constrained determinantal point process…

One-shot Robust Federated Learning of Independent Component Analysis

arXiv:2505.20532v2 Announce Type: replace Abstract: This paper studies robust one-shot aggregation for distributed and federated Independent Component Analysis (ICA). In this setting, each client computes a local ICA…

Learning Auditable Classifier Models: Source-Disjoint Tree Ensembles

arXiv:2608.15725v1 Announce Type: new Abstract: Predictive models in clinical and regulated settings must be accurate and fully auditable. Tree ensembles deliver strong accuracy on tabular data, but their sequential…

Do Language Models Consistently Encode the Current Year?

arXiv:2608.15507v1 Announce Type: cross Abstract: A consistent concept of the current time is important for temporal reasoning, yet how language models represent the current time is not well understood. We contribute…

Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam

arXiv:2607.03998v4 Announce Type: replace Abstract: The local sharpness of the loss, the top Hessian eigenvalue $\lambda_1$, determines the largest stable gradient step, but measuring it normally requires Lanczos or…

Characterization of Thermal Systems from Noisy and Low-resolution Measurements Using Dynamic Mode Decomposition

arXiv:2608.14581v1 Announce Type: cross Abstract: Thermal monitoring in practical applications is often constrained by sparse sensing, measurement noise, and limited spatial resolution, which hinder the identification…

PathFinder: Joint Decompositions of Linked Multimodal Datasets

arXiv:2608.14951v1 Announce Type: new Abstract: Low-rank matrix decompositions can uncover patterns and structure in data and have a number of different applications across many disciplines. Extensions to "joint"…

Proteus: Incremental Memory Activation for Long-Context Sequence Modeling

arXiv:2608.16844v1 Announce Type: new Abstract: The quadratic cost of attention-based sequence models for long contexts has motivated a growing line of research on memory-based models that can compress context into a…

Interpretable Cross-Lingual Alignment in Small Language Models: Probing Cultural and Pragmatic Reasoning in Japanese-English Bilingual LLMs

arXiv:2608.14896v1 Announce Type: cross Abstract: Large language models work well on English and behave in poorly understood ways on languages typologically far from it. Japanese is a clean example, where evaluation…

Language models suffer from a curse of ambiguity

arXiv:2608.15448v1 Announce Type: cross Abstract: Large language models increasingly rely on sampling as a driver of their own improvement, making the fidelity of their learned distributions more critical than ever.…

Integrating Persuasion Theory into the Epidemiological Modelling of Health Misinformation Spread on Social Media

arXiv:2608.15689v1 Announce Type: cross Abstract: This study presents a hybrid epidemiological and behavioural framework to simulate the spread of health misinformation on social media. We extend the classical…

When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval

arXiv:2608.16502v1 Announce Type: new Abstract: Large-scale agents increasingly rely on retrieval to access external capabilities. We study this retrieval gate in structured tools and APIs, a measurable class of…

Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification

arXiv:2608.14929v1 Announce Type: cross Abstract: Open-weight language models are fine-tuned, quantized, pruned, and merged, yet their provenance is often undocumented. We study data-free white-box lineage verification:…

Pallas: A Proactive KV Cache Migration Framework for LLM Inference in AI-RAN

arXiv:2608.16477v1 Announce Type: new Abstract: AI-RAN brings large language model (LLM) serving close to mobile users, but cellular handover can separate an active request from its inference state: the user attaches to…

SubZero+: Efficient Zeroth-Order LLM Fine-Tuning via Large Learning Rates

arXiv:2608.15665v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables backpropagation-free fine-tuning of large language models, but existing ZO methods suffer from high-variance gradient estimators,…

Real-Time State-of-Health Estimation and Online Degradation Prognosis from Partial Battery Discharge Using Physics-Informed Neural Networks

arXiv:2608.14764v1 Announce Type: new Abstract: With the increasing integration of renewable energy sources, energy storage systems have become essential, making the accurate estimation of their State of Health (SOH)…

ER-KANs: Efficient and Robust Kolmogorov-Arnold Networks for Data-Scarce Scientific Machine Learning

arXiv:2608.14773v1 Announce Type: new Abstract: The efficient-KAN literature---covering Chebyshev, wavelet, and radial-basis-function variants of the original Kolmogorov-Arnold Network---has been benchmarked almost…

LUNG-KGMM: Knowledge-Guided Multimodal Learning for Lung Cancer Incidence Prediction

arXiv:2608.14657v1 Announce Type: new Abstract: Early identification of lung cancer risk is critical for timely intervention, yet existing prediction models are limited by their reliance on single data modalities and…

Generalised Transportability via Causal Abstractions

arXiv:2608.15645v1 Announce Type: new Abstract: Transporting a causal conclusion from a source study population to a target one is a fundamental problem in causal inference. The theory of transportability provides a…

Uncovering Hidden Leptonic Correlations with Flow Matching and Autoencoders

arXiv:2608.15042v1 Announce Type: cross Abstract: We perform a global search for values of the Yukawa matrices and Majorana masses in the Type-I seesaw mechanism. Using flow matching, which is a generative artificial…

A Generative Deep Learning Workflow for Inverse Molecular Design of Fuels

arXiv:2504.12075v4 Announce Type: replace Abstract: In the present work, a generative deep learning framework combining a Co-optimized Variational Autoencoder (Co-VAE) with quantitative structure-property relationship…

ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

arXiv:2607.27924v3 Announce Type: replace Abstract: In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to…

The Limits of Binding in Dual Encoders

arXiv:2608.15971v1 Announce Type: new Abstract: Dual-encoder models such as CLIP score an image-caption pair by a single inner product of two independently computed unit vectors, and fail at binding, often scoring near…

An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learning

arXiv:2608.15153v1 Announce Type: cross Abstract: Differentially private federated learning must balance privacy protection against model accuracy and training efficiency. Static gradient clipping applies a fixed…

RecurrentGPT: Expressive Depth through Recurrent Modulation in Transformers

arXiv:2608.15062v1 Announce Type: cross Abstract: Scaling transformer language models creates an inherent tension between expressivity and memory efficiency. While unique weights across layers preserve functional…

NRCD: An Open Database of Collegiate Running with Unified Performance Standardization

arXiv:2608.14776v1 Announce Type: new Abstract: Collegiate running in the United States generates thousands of race results annually in cross country and track and field, yet no large-scale dataset has been publicly…

From Fixed Grids to Moving Particles:A Transferable Latent Operator for Fluid Dynamics

arXiv:2608.14120v2 Announce Type: replace Abstract: Lagrangian modeling is vital to fluid dynamics, as it characterizes particle transport and complements the Eulerian representation. However, Lagrangian trajectories…

RouteTS: Frequency-Time Routing for Time Series Forecasting

arXiv:2608.14682v1 Announce Type: new Abstract: Real-world time series inherently intertwine global periodic structures with localized non-stationary variations. Existing approaches process these heterogeneous dynamics…

Foresight-England: Development of a National-Scale Generative AI Model of Electronic Health Records for Medical Event Prediction across the COVID-19 Pandemic

arXiv:2608.16273v1 Announce Type: new Abstract: Foresight-England (Foresight-E) is the first national-scale generative foundation model of electronic health records (EHRs), developed as a research pilot strictly for…

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

arXiv:2608.16072v1 Announce Type: new Abstract: Reinforcement learning (RL) with group-relative advantages has become the de facto standard for post-training language model reasoners. However, when optimizing multiple…

Group ICA 2.0: Closing the Gap Between Subjects and Group Latent Decomposition with Copula-Linked Group ICA (CoLiG-ICA)

arXiv:2608.16029v1 Announce Type: new Abstract: Group Independent Component Analysis (gICA) is widely used to decompose high-dimensional functional MRI data into interpretable brain networks. However, conventional gICA…

A Scalable Pipeline for LLM-Teacher Distillation Labeling: Work-Stealing Job Scheduling and Memory-Aware GPU Concurrency

arXiv:2608.15975v1 Announce Type: cross Abstract: Labeling large text corpora with LLM teachers has become a practical route to training data at scale. At millions of items, hand-labeling every batch is not feasible,…

Density-Reweighted Entropic Optimal Transport: Decoupling Geometry from Sampling Density

arXiv:2608.16506v1 Announce Type: cross Abstract: Dataset alignment is a central step in data analysis across science and engineering, where the goal is to match observations between datasets. Entropic Optimal Transport…

Uncertainty Identifies Difficult Samples Across Methods: A Multi-Task Study on a Heterogeneous Skin Lesion Dataset

arXiv:2608.14768v1 Announce Type: cross Abstract: Skin lesion classifiers can be confidently wrong on the cases that matter most, so knowing when a prediction should not be trusted is clinically as useful as the…

Adaptive Optimization via Momentum on Variance-Normalized Gradients

arXiv:2602.10204v2 Announce Type: replace Abstract: We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two complementary…

Learning Koopman operators for coupled systems via information on governing equations of subsystems

arXiv:2605.01835v2 Announce Type: replace Abstract: Nonlinear coupled systems are ubiquitous in science and engineering. The analysis and modeling of such systems are challenging due to their high dimensionality and…

Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities

arXiv:2501.12147v2 Announce Type: replace-cross Abstract: Selecting appropriate training data is crucial for instruction fine-tuning of large language models (LLMs), which aims to (1) elicit strong capabilities, and (2)…

DualMiT-Net: Local-Global Transformer-Convolutional Fusion for Breast Mass Segmentation in Mammographic Regions of Interest

arXiv:2608.15019v1 Announce Type: cross Abstract: Breast mass segmentation is an important step in computer-aided mammography, but it remains difficult because masses can have low contrast, irregular shapes, and…

INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval

arXiv:2608.16203v1 Announce Type: cross Abstract: Existing speech retrieval systems rely on fixed similarity matching and cannot adapt to diverse user intents. We introduce INSPIRE, the first benchmark for…

Clause Encounters of the Third Kind: Can LLMs Replace Language Teachers?

arXiv:2608.16286v1 Announce Type: new Abstract: While various organizations now actively encourage LLM use in classrooms, we still lack rigorous, systematic evaluations of how well these models actually perform the…

MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models

arXiv:2606.05177v2 Announce Type: replace Abstract: Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and text. We…

HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory

arXiv:2608.16114v1 Announce Type: new Abstract: As agentic tasks grow in complexity, LLM agents increasingly rely on experiential memory to reuse procedural knowledge across tasks. Effective memory design must jointly…

Personalized Auto-Research: Towards a True AI Co-Scientist

arXiv:2608.14881v1 Announce Type: cross Abstract: AI co-scientists that generate hypotheses, retrieve related work, design experiments, execute code, and draft full papers are beginning to change how research is carried…

DA-RAC: Distance-Aware Calibration of LLM Judges for Trustworthy AI Auditing

arXiv:2608.14950v1 Announce Type: new Abstract: Generative AI systems are increasingly producing real-world artifacts, however their efficacy and validity are often evaluated via context-free LLM-scoring. These judges…

From Positionwise Confidence to Prefix Scheduling: Verifier Skipping in Speculative Decoding

arXiv:2608.14787v1 Announce Type: cross Abstract: Speculative decoding is a leading technique to reduce the cost of autoregressive generation by using a small drafter to propose several tokens, which are then verified…

RamseyGadgets: A Graph Construction Dataset for LLMs

arXiv:2608.14999v1 Announce Type: new Abstract: Constructing special graphs is an important task within graph theory and computer science. Many popular graph constructions are the result of a comprehensive exploration…

A Cognitively Motivated Multidimensional Framework for Evaluating Metaphor Explanations

arXiv:2608.15828v1 Announce Type: new Abstract: Current evaluation of metaphor explanations relies mainly on holistic quality ratings, revealing little about how explanation quality is structured or where human…

Does the LM Head Create a Harmful Gradient Bottleneck? A Causal Test

arXiv:2608.16671v1 Announce Type: new Abstract: The language-model head maps a hidden state of width D to a vocabulary of size V, so its transpose can return at most D independent directions to the Transformer. Godey…

Discovering Conceptual Metaphors Across Topics and Media Types

arXiv:2608.06652v2 Announce Type: replace Abstract: Conceptual metaphors guide our thinking and actions by allowing us to reason about more abstract experiences (e.g., paying taxes) in terms of more concrete or embodied…

HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

arXiv:2602.13964v4 Announce Type: replace Abstract: Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models on challenging, multi-domain questions. However,…

Hypergraph as Language

arXiv:2605.21858v2 Announce Type: replace Abstract: Large language models (LLMs) have recently shown strong potential in modeling relational structures. However, existing approaches remain fundamentally graph-centric:…

Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors

arXiv:2608.16707v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as decision-making agents in settings that require sophisticated environmental exploration. However, existing work…

When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs

arXiv:2608.11403v2 Announce Type: replace-cross Abstract: Self-consistency via majority vote reduces per-problem accuracy on most GPQA Diamond problems for small instruction-tuned models: 56.6% of problems for…

Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form

arXiv:2608.15022v1 Announce Type: cross Abstract: Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it flexibly. What…

Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents

arXiv:2608.15071v1 Announce Type: cross Abstract: Learning from experience is critical for developing capable, self-improving large language model (LLM) agents. Existing methods typically extract knowledge from…

From Prompts to Constructs: A Dual-Validity Framework for Large Language Model Research in Psychology

arXiv:2506.16697v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are entering psychological research both as tools and as objects of inquiry. Yet many studies apply human instruments to LLMs…

Time as Structure: Temporal Dependency Graphs for Verifiable Deadline Computation over Legal Documents

arXiv:2608.15270v1 Announce Type: new Abstract: Miss a filing deadline by one day and the claim is barred, however strong the case. Computing that deadline is rarely simple: the period runs from a triggering event, is…

VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding

arXiv:2608.14718v1 Announce Type: cross Abstract: Video understanding is a fundamental task for evaluating the capabilities of multimodal large language models (MLLMs). However, existing leading models have already…

The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines

arXiv:2608.14588v1 Announce Type: cross Abstract: Sequential multi-agent LLM pipelines chain specialized agents without verification at handoffs, creating a structural flaw with measurable and severe consequences. We…

The Machine's Internal Clock: Do LLMs Share Human Temporal Illusions?

arXiv:2608.15394v1 Announce Type: new Abstract: Human perception of time is subjective. Well-documented temporal illusions show that the brain relies on context and relational cues for judging duration instead of…

Domain Agnostic Text Redaction from Natural Language Rules using Instruction Tuning

arXiv:2608.14693v1 Announce Type: new Abstract: With the increasing digitization of personal and corporate communication, the automatic sanitization of textual data has become a crucial component of data privacy and…

CulTrace: Tracing Internal Cultural Reasoning in Large Language Models

arXiv:2508.08879v3 Announce Type: replace Abstract: The growing deployment of large language models (LLMs) across diverse cultural contexts necessitates a deeper understanding of models' hidden representations of…

Efficient Code Embeddings from Code Generation Models

arXiv:2508.21290v2 Announce Type: replace Abstract: jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify…

STAIR: Semantic-Temporal Automaton for Interpretable Reasoning in Temporal Question Answering

arXiv:2608.16224v1 Announce Type: new Abstract: By leveraging large-scale pretraining, LLMs can interpret diverse temporal expressions and question formulations without task-specific training. However, existing…

MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations

arXiv:2608.15844v1 Announce Type: new Abstract: Long-horizon, multi-agent language model (LM) simulations are widely proposed for studying social behavior, yet instruments to measure whether persona-conditioned agents…

Schema-Agnostic Graph Reasoning Agent for Hybrid Knowledge Graphs

arXiv:2608.15834v1 Announce Type: cross Abstract: Tool-calling LLM agents navigate unfamiliar codebases with a handful of generic primitives for listing, reading and searching files (ls, cat, grep). A knowledge graph…

Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs

arXiv:2603.02830v2 Announce Type: replace Abstract: Predicting future student responses to questions is particularly valuable for educational learning platforms where it enables effective interventions. One of the key…

Do Value Vectors in Deep Layers Need Context from the Residual Stream?

arXiv:2606.02780v4 Announce Type: replace Abstract: The success of the transformer architecture as the backbone of modern LLMs is in large part due to its use of attention layers. An attention layer follows the standard…

When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation

arXiv:2608.16515v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trust problem: retrieved…

Neurosymbolic Embodied Agents

arXiv:2608.16794v1 Announce Type: cross Abstract: Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dynamics or act on…

LLMs Get Smarter from Targeted Synthetic Multilingual Data

arXiv:2608.15964v1 Announce Type: new Abstract: Language-specific competency (LSC) is the phenomenon of a language model performing better or worse depending on the language of the prompt. In other words, a language…

A Pilot Study of Autocompleting Tokenizers

arXiv:2608.15080v1 Announce Type: new Abstract: Modern input methods routinely rely on autocomplete to omit information that can be recovered from local context. Inspired by these autocomplete-assisted writing systems,…

Douyin Multimodal Embedding Model Technical Report

arXiv:2608.02148v2 Announce Type: replace-cross Abstract: Multimodal representation learning is a cornerstone of modern AI. By encoding multimodal queries and targets into vectors, it powers industrial search and…

PLSQLBench: Benchmarking LLM Systems for Executable Procedural Database Programming

arXiv:2608.15931v1 Announce Type: new Abstract: We present PLSQLBench, to our knowledge the first benchmark for evaluating whether LLMs can write executable PL/SQL programs, with correctness measured through…

Skill2Query: Exploiting Skill Structure to Generate Pseudo-Queries for Agent Skill Retrieval

arXiv:2608.16071v1 Announce Type: new Abstract: Pseudo-query generation can alleviate the supervision bottleneck for agent skill retrieval, but existing document-level approaches typically leave the rich internal…

A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models

arXiv:2608.15102v1 Announce Type: new Abstract: We investigate whether Mixture-of-Experts (MoE) language models develop linguistically structured expert routing during bilingual language acquisition. Inspired by the…

Counting Documents Is Not Counting Text: Unit Bias in Web-PDF Corpus Statistics

arXiv:2608.16390v1 Announce Type: new Abstract: PDF corpora advertise their size in tokens but compute every rate they publish (coverage, OCR routing, re-fetch recovery, language mix) per document, and none decomposes…

Path2ST: Hierarchical Cell-Tissue Grounded Cross-Modal Translation for Spatial Transcriptomics

arXiv:2608.14710v1 Announce Type: cross Abstract: Predicting spatial gene expression from hematoxylin and eosin (H\&E)-stained images offers a cost-effective alternative to spatial transcriptomics (ST). However,…

BabelSteering: Multilingual Safety Alignment via English Steering Vectors

arXiv:2608.16577v1 Announce Type: new Abstract: Large language models (LLMs) are deployed globally in high-stakes settings, yet most safety research and alignment efforts remain concentrated on English. Thus, users…

Demographic Injection in Medical Language Models under Diversity, Equity, and Inclusion Prompts

arXiv:2608.15254v1 Announce Type: cross Abstract: Clinical-AI guidance increasingly recommends prompting language models to reason with attention to diversity, equity, and inclusion (DEI). We measure a side effect that…

GALA: Generation-Aware Cross-Modal Alignment for Text-to-Time-Series Synthesis

arXiv:2608.13741v2 Announce Type: replace Abstract: Synthesizing time series from natural language is emerging as the most expressive form of controllable time series generation. However, existing text-conditioned…

EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory

arXiv:2608.12627v2 Announce Type: replace-cross Abstract: Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences. We demonstrate two bottlenecks in…

Class Imbalance and Batch Effects in LLM-Based Screening for Systematic Reviews

arXiv:2608.14737v1 Announce Type: new Abstract: This study analyses LLMs in imbalanced binary classification, using study screening in systematic reviews as the application domain. An experiment was conducted in five…

STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment

arXiv:2608.16553v1 Announce Type: new Abstract: Multi-preference alignment is often framed as scalarization: combine reward dimensions, then optimize. This leaves a temporal decision underspecified: when should each…

FollowUpBot: An LLM-Based Conversational Robot for Automatic Postoperative Follow-up

arXiv:2507.15502v1 Announce Type: cross Abstract: Postoperative follow-up plays a crucial role in monitoring recovery and identifying complications. However, traditional approaches, typically involving bedside…

Why Vision Fails as a Universal Bridge: Rectifying Modality Asynchrony in Multilingual MLLMs

arXiv:2608.15085v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) exhibit substantial performance degradation in non-English visual reasoning, despite the strong multilingual competence of their…

BridgeAlign: Bridging Preference Alignment for Humanities and Social Sciences

arXiv:2607.27366v2 Announce Type: replace Abstract: While data synthesis for large language models (LLMs) is prevalent, it primarily targets domains with verifiable answers, overlooking open-ended humanities and social…

Semantic Space of Parts of Speech

arXiv:2608.15443v1 Announce Type: new Abstract: Parts of speech categorization is understood in the European linguistic tradition as crisp categorization, which is also reflected in corpus linguistics, where each…

SEER: Long-Context Reasoning via Selective Visual-Text Compression

arXiv:2608.15962v1 Announce Type: new Abstract: Long-context reasoning remains computationally expensive for large language models due to the quadratic complexity of attention over text tokens. Visual-text compression…

Beyond Single Object: Learning 3D Relations with Large Language Models

arXiv:2608.15710v1 Announce Type: cross Abstract: We address a fundamental gap in 3D-LLMs: existing models focus on single-object/scene description, struggling with detailed, inter-object comparison. We propose a…

Inference-Time Mitigation of Adversarial Political Bias in Large Language Models

arXiv:2608.14629v1 Announce Type: new Abstract: As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and invulnerable to…

Large language model-assisted discovery of cohorts from scientific literature

arXiv:2608.15909v1 Announce Type: cross Abstract: Background: Planning multi-study analyses requires identifying cohorts with the relevant participants, phenotypes, and data modalities. This process commonly relies on…

LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering

arXiv:2608.07370v2 Announce Type: replace Abstract: Scientific literature is increasingly used as a knowledge source for language models, retrieval-augmented generation systems, and research assistants, but answering…

mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA

arXiv:2411.15041v2 Announce Type: replace-cross Abstract: Advanced Multimodal Large Language Models (MLLMs) struggle with recent Knowledge-based Visual Question Answering (VQA) tasks, such as INFOSEEK and…

Bye-bye, Bluebook? Automating Legal Drudgery With AI-Augmented Rule Following

arXiv:2505.02763v2 Announce Type: replace Abstract: One of the central promises of legal AI is to automate drudgery -- the formal, repetitive tasks of lawyers' work that consume time without calling for much discretion.…

MoRFI: Monotonic Sparse Autoencoder Feature Identification

arXiv:2604.26866v2 Announce Type: replace Abstract: Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction. Subsequent stages of post-training…

PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy

arXiv:2608.16650v1 Announce Type: new Abstract: Large language models (LLMs) exhibit sycophancy, a tendency to agree with user beliefs regardless of factual accuracy. This can reinforce misconceptions, but eliminating…

Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks

arXiv:2501.06286v2 Announce Type: replace Abstract: Multi-hop question answering requires a system to identify and integrate evidence distributed across documents, yet large language models remain vulnerable to…

BengaliMCQ: Automatic Generation and Answer Prediction of Academic Multiple-Choice Questions in a Low-Resource Language

arXiv:2608.15547v1 Announce Type: new Abstract: Traditional retrieval-augmented generation (RAG) frameworks process documents without attending to their hierarchical structure, leading to poor performance, especially in…

One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL

arXiv:2608.12253v2 Announce Type: replace Abstract: Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach…

Enhancing Science Classroom Discourse Analysis through Joint Multi-Task Learning for Reasoning-Component Classification

arXiv:2604.21137v3 Announce Type: replace Abstract: Analyzing the reasoning patterns of students in science classrooms is critical for understanding knowledge construction mechanism and improving instructional practice…

Wiola 13M, a Gated Spiral Attention Architecture for Parameter Efficient Small Language Models

arXiv:2608.14604v1 Announce Type: new Abstract: Small language models in the ten to one hundred million parameter range are attractive for on device inference, rapid experimentation, and controlled scientific study, yet…

KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving

arXiv:2608.15797v1 Announce Type: cross Abstract: KV-cache eviction caps the memory cost of long reasoning traces but is inherently lossy because the model decodes from a partial view of its history. Under aggressive…

PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning

arXiv:2508.09521v3 Announce Type: replace Abstract: Emotional support conversations require more than fluent responses. Supporters need to understand the seeker's situation and emotions, adopt an appropriate strategy,…

Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers

arXiv:2607.23811v2 Announce Type: replace-cross Abstract: Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple's most powerful on-device…

Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text

arXiv:2608.16868v1 Announce Type: new Abstract: A language model's output does not by itself provide verifiable evidence about the internal computation that produced it. We study computational provenance: whether…

MobileMem: Learning from a Year of Mobile Experiences

arXiv:2608.13606v2 Announce Type: replace-cross Abstract: The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand,…

Vision Language Models Cannot Plan, but Can They Formalize?

arXiv:2509.21576v2 Announce Type: replace Abstract: The advancement of vision language models (VLMs) has empowered embodied agents to accomplish simple multimodal planning tasks, but not long-horizon ones requiring long…

DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models

arXiv:2608.14632v1 Announce Type: new Abstract: Diffusion large language models (D-LLMs) have emerged as a promising paradigm for text generation. However, similar to autoregressive LLMs, D-LLMs remain vulnerable to…

Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning

arXiv:2608.16554v1 Announce Type: new Abstract: Answer-only reinforcement learning (RL) trains reasoning models to solve fully specified problems, but many realistic queries omit a premise needed for a unique answer. In…

Computational KJ-Ho: An Analyst-Bias-Free Insight Extraction Framework from Large-Scale Qualitative Data Using Domain-Specialized LLMs

arXiv:2608.16467v1 Announce Type: cross Abstract: The qualitative research methodologies that underpin consumer-insight generation - the KJ method, Grounded Theory, and Thematic Analysis - share a structural constraint:…

DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption

arXiv:2608.16536v1 Announce Type: cross Abstract: Multimodal Retrieval Augmented Generation (M-RAG) is increasingly vulnerable to adversarial attacks where malicious data are crafted to produce embeddings that align…

Language Models that Think, Chat Better

arXiv:2509.20357v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) trains language models to use long chain-of-thought reasoning (CoT) in domains like mathematics and code with…

Does a Tool Result Carry More Authority Than Plain Text? Three Prospective Studies of False-Claim Adoption in a Synthetic Assignment Task with Claude Opus 5

arXiv:2608.14992v1 Announce Type: cross Abstract: Language-model systems increasingly read from stores they also write to, so a claim that was merely written earlier can return looking retrieved. We tested whether the…

PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows

arXiv:2607.06008v3 Announce Type: replace-cross Abstract: While Large Language Model (LLM) agents excel at monolingual long-horizon planning and tool use, enterprise workflows inherently require processing multilingual…

Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models

arXiv:2608.14797v1 Announce Type: new Abstract: Large language models (LLMs) and large vision-language models (LVLMs) have demonstrated impressive generative capabilities, yet ensuring their outputs align with user…

TaoLive Digital Avatar Agent Technical Report: Training Agents to Evolve with Their Harness

arXiv:2608.15763v1 Announce Type: new Abstract: AI-powered digital-avatar streamers in live e-commerce must answer product questions, engage viewers, and execute changing business strategies in real time. This requires…

Reasoning-Based Personalized Generation for Users with Sparse Data

arXiv:2602.21219v2 Announce Type: replace Abstract: Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history. However, real-world users usually…

When Do Concepts Become Functionally Sufficient During Language-Model Training?

arXiv:2608.15323v1 Announce Type: new Abstract: Understanding a model and its learning mechanisms in depth requires identifying when its internal structures become useful, rather than simply looking at the final state.…

ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement

arXiv:2608.16011v1 Announce Type: new Abstract: We introduce ReRef-3D, a benchmark for language-guided placement in 3D scenes. It contains 33,826 instructions across 998 CLEVR-derived scenes, spanning 16 placement…

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

arXiv:2608.16002v1 Announce Type: new Abstract: Reliable uncertainty quantification (UQ) is essential for deploying large language model (LLM) agents in complex interactive environments. Existing UQ methods largely rely…

D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understanding

arXiv:2608.16417v1 Announce Type: new Abstract: Multi-modal retrieval-augmented generation (RAG) is a key technique for visually rich long document understanding. Existing multi-modal RAG methods are progressively…

Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers

arXiv:2606.21037v2 Announce Type: replace-cross Abstract: The empirical foundation of cyber deception relies on human-centered hypotheses, but the rapid emergence of autonomous, AI-enabled attackers challenges whether…

Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency

arXiv:2608.16003v1 Announce Type: cross Abstract: Automated checking pipelines increasingly place one language model as the checker and another (or the same one) as the fixer. We ask whether that wiring changes what the…

SymbolicLight V1: Spike-Gated Dual-Path Language Modeling at High Activation Sparsity

arXiv:2605.21333v2 Announce Type: replace Abstract: Natively trained spiking language models must preserve information across time while operating through sparse binary activations, a combination that has produced a…

When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness

arXiv:2608.16627v1 Announce Type: new Abstract: Natural language explanations (NLEs) are increasingly used as inputs, for example, as few-shot rationales that influence model behavior in in-context learning (ICL).…

DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models

arXiv:2505.14107v5 Announce Type: replace Abstract: The emergence of groundbreaking large language models capable of performing complex reasoning tasks holds significant promise for addressing various scientific…

Coverage Is Not Containment: A Fundamental Limit of Admission-Time Defenses Against Coordinated Poisoning of Vector Retrieval

arXiv:2608.16044v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) answers a question by retrieving passages from a vector store and trusting them as context, so anyone who can add documents can try…

Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning

arXiv:2608.16333v1 Announce Type: new Abstract: On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories. This approach has achieved strong empirical…

Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning

arXiv:2608.16316v1 Announce Type: cross Abstract: Large Multimodal Models (LMMs) for video reasoning have long been hindered by the high computational cost of processing vast amounts of visual information. This dilemma…

Mitigating Bias in Locally Constrained Decoding via Tractable Proposals

arXiv:2606.01926v2 Announce Type: replace Abstract: Generations from large language models often fail to conform to desired constraints such as JSON schema. Existing locally constrained decoding (LCD) approaches enforce…

DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech

arXiv:2608.16053v1 Announce Type: new Abstract: Synthetic conversational speech has become an important resource for developing and evaluating conversational speech systems. However, existing dialogue synthesis…

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

arXiv:2608.14577v1 Announce Type: new Abstract: Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis. Consequently,…

Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis

arXiv:2608.15630v1 Announce Type: cross Abstract: The rapid development and growing deployment of large language models (LLMs) have made it increasingly important to understand their capabilities. A common approach is…

DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization

arXiv:2412.07672v2 Announce Type: replace-cross Abstract: Large language models (LLMs) remain vulnerable to jailbreak attacks in which adversarial prompts induce harmful outputs. Existing defenses often require access…

Multimodal Language Models Benchmarked Against the NRC Reactor Operator Licensing Examination: Fine-Tuning and Retrieval Strategies

arXiv:2607.22067v2 Announce Type: replace Abstract: Competence claims for a language model in a safety-critical domain are credible when measured against a standard the domain already enforces. We evaluate an…

Token Distribution versus Data Volume: Domain Balancing in Multi-Domain Meeting Summarisation

arXiv:2608.15935v1 Announce Type: new Abstract: Jointly fine-tuning an LLM on meeting-summarisation corpora of widely varying size raises a question that prior work leaves confounded: when a domain-balanced training…

Why Summaries Turn Neutral: Policy Attribution for Sentiment Drift in Reinforcement Learning from Human Feedback

arXiv:2608.15530v1 Announce Type: new Abstract: Reinforcement learning with human feedback (RLHF) aligns LLMs with human preferences, improving summarization fluency and safety, but causes sentiment drift: overly…

Where did the ambiguity go? Examining how multimodal models interpret polysemous words

arXiv:2608.00410v2 Announce Type: replace-cross Abstract: Human language is highly polysemous. Many common words (e.g., "bank" or "palm") carry several distinct meanings that shape what humans communicate and imagine.…

$x$-Prediction Flow: Efficient Continuous Decoding for Masked Diffusion Language Models

arXiv:2606.29066v2 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens, but their standard decoder reduces each step to a binary action: a position is…

A validity-guided workflow for robust large language model research in psychology

arXiv:2507.04491v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are rapidly being integrated into psychological and behavioral research as research tools, evaluation targets, human simulators, and…

PolyDebate: A Game-Orchestrated Multimodal System for Debate Skills Practice and Evaluation

arXiv:2608.16276v1 Announce Type: cross Abstract: Debate is a structured form of persuasive communication that trains argument construction, rebuttal, oral delivery, and audience awareness. These skills are valued in…

BiAxisBias: Evaluating LLM Bias Beyond a Single Prompt and a Single Explanation

arXiv:2605.09041v2 Announce Type: replace Abstract: LLM bias scores can depend on audit design. We introduce BiAxisBias, a prespecified audit varying task, role, perspective, sentiment, and wording over 200 stereotype…

Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models

arXiv:2608.16647v1 Announce Type: new Abstract: On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization behavior remains…

Analyzing Speech Condition Effects in Dysarthric ASR: A Layer-wise Probing Study

arXiv:2608.01865v2 Announce Type: replace Abstract: Automatic speech recognition (ASR) performance degrades sharply on dysarthric speech, yet how disordered articulation reshapes a model's internal representations is…

VTInstructor: Visual Trajectory Prompting for Navigation Instruction Generation in Continuous Environments

arXiv:2608.15284v1 Announce Type: cross Abstract: Navigation instruction generation from ego-centric RGB video in continuous environments is an important yet challenging task for human-robot interaction and scalable…

The Commercial Tax: Rent-vs-Own Blind Spots in Multi-Hop Retrieval Benchmarks

arXiv:2608.16096v1 Announce Type: cross Abstract: Enterprises connect language models to their own data through retrieval. The benchmarks that rank multi-hop retrieval systems leave out two facts a buyer needs before a…

jina-vlm: Small Multilingual Vision Language Model

arXiv:2512.04032v4 Announce Type: replace Abstract: We present jina-vlm, a token-efficient 2.4B parameter vision-language model that achieves state-of-the-art multilingual VQA performance among open 2B-scale VLMs. The…

Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning

arXiv:2608.16620v1 Announce Type: new Abstract: Palmyra x6 is a large language model optimized for use with enterprise-oriented agentic tasks. The model was built by post-training a Mixture-of-Experts base model with…

SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice

arXiv:2606.04155v2 Announce Type: replace-cross Abstract: Social skills such as negotiation and leadership are crucial for personal and professional success in today's interconnected world. However, scalable and…

Unadapted Multilingual ASR on a Garrusi Kurdish Evaluation Set: A Common-Reference Staged Normalization Analysis

arXiv:2608.16379v1 Announce Type: new Abstract: Evaluating speech recognition for a Kurdish variety written in a Latin field orthography, using a model that outputs Arabic script, creates a measurement problem before a…

The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models

arXiv:2606.05183v2 Announce Type: replace Abstract: Pass/fail safety evaluation reports whether a model refused. It does not report how far a model went to please the user, and we show these are close to different…

Iterative Self-Learning for Expressive Text-to-Speech Synthesis

arXiv:2608.15910v1 Announce Type: cross Abstract: Expressive text-to-speech (TTS) systems that use explicit conditioning labels provide direct and interpretable control over expressive attributes, in contrast to…

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

arXiv:2606.06087v2 Announce Type: replace Abstract: Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context…

Model Hypnosis: Strong control of AI via additive subliminal effects

arXiv:2608.16834v1 Announce Type: new Abstract: We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues in the prompt can be…

Executable Code Knowledge: Code as a Native, Validation-Carrying Knowledge Representation for AI Coding Agents

arXiv:2608.16295v1 Announce Type: new Abstract: AI coding agents need more than relevant snippets: they need business semantics, validation evidence, relations, and assurance that their context is current. Existing…

Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization

arXiv:2608.16539v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) have made rapid progress on standardized benchmarks, yet their deployment in practical media workflows, curation, archival indexing,…

FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue

arXiv:2608.16303v1 Announce Type: new Abstract: Long-term emotional-support agents require memory mechanisms for personalized understanding across sessions. However, emotional-support dialogue is often low-density:…

Using the Mimi codec for metalinguistic representations

arXiv:2608.15799v1 Announce Type: new Abstract: In this paper, we focus on the dictionary of 2048 tokens used in Mimi semantic token codebook, the neural codec of the Moshi language model. We show that the ABX…

CAPO: Constraint-Aware Prompt Optimization for LLM Agents

arXiv:2608.16068v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks. Such deployments impose distinct operational…

Closing the Affective Loop: Multimodal Speaker-Listener Emotion-Dynamics-Aware Empathetic Social Robots

arXiv:2608.16686v1 Announce Type: cross Abstract: Empathetic social robots should respond not only to what users say, but also to how their emotions dynamically evolve during interaction. However, existing empathetic…

Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints

arXiv:2608.15032v1 Announce Type: new Abstract: Converting a set of architectural blueprints into a complete material quantity takeoff requires visual perception across drawing sheets, dimensional and multi-hop…

Hallucination Span Detection with Input-Side Evidence Alignment

arXiv:2608.15804v1 Announce Type: new Abstract: Hallucinations remain a major obstacle to the reliable use of large language models (LLMs) in conditional text generation. Existing methods primarily assess the factuality…

HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals

arXiv:2608.16353v1 Announce Type: new Abstract: Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stakes deployments. These…

On the Role of Directionality in Structural Generalization

arXiv:2607.02307v2 Announce Type: replace Abstract: Several SLOG test categories explicitly involve directional distinctions (modifier position shifts, argument extraction positions), yet AM-Parser, the previous SOTA,…

Propaganda Forensics: Recovering the Generation Pipeline of an AI-Driven Influence Campaign

arXiv:2608.15746v1 Announce Type: cross Abstract: We present a forensic analysis of the generation pipeline behind a recent AI-driven influence campaign. We introduce PROPAGIA, a corpus of 2,646 propagandist French…

The First ChineseBabyLM Challenge: training data-efficient and cognitively plausible language models for Chinese

arXiv:2607.10745v2 Announce Type: replace Abstract: This paper presents the first ChineseBabyLM Challenge, organized as part of NLPCC 2026. The challenge asked participants to train language models from scratch using no…

Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection

arXiv:2608.12652v2 Announce Type: replace Abstract: Benchmark contamination is diagnosed with n-gram overlap, likelihood-based membership inference, or canary strings, and each needs something usually unavailable: the…

LENS: In-Context Search via Latent Evidence Exploration over Dynamic Raw Documents

arXiv:2608.16185v1 Announce Type: new Abstract: LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages,…

Wiktionary as a Crowdsourced Lexicon for English Dialects

arXiv:2608.15641v1 Announce Type: new Abstract: This paper evaluates Wiktionary as an ethically crowdsourced lexicon for English dialects. We took a two-phase approach, providing an in-depth descriptive analysis of the…

When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations

arXiv:2608.15654v1 Announce Type: new Abstract: Large language models can write fluent stories, but open-ended storytelling requires more than local fluency. In evolving world simulations and AI-native games, models…

Gated Against One Model, Open to the Next: Option-Only Solvability in Legal Multiple-Choice Benchmarks

arXiv:2608.15428v1 Announce Type: new Abstract: Multiple-choice benchmarks are graded on whether a model picks the right option, not on whether it needed the question. Measuring that gap takes care: a model answering A…

Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression

arXiv:2604.04120v2 Announce Type: replace Abstract: Long chain-of-thought (Long-CoT) reasoning models have motivated a growing body of work on compressing reasoning traces to reduce inference cost, yet existing…

Writing Style Similarity Reflects Academic Genealogy

arXiv:2608.14843v1 Announce Type: new Abstract: As authorship attribution systems are increasingly deployed to detect ghostwritten and AI-generated papers, their errors can support accusations against legitimate…

When AI Rewrites, Classifiers Relax: Uncertainty-Aware Sentiment Analysis on Sarcastic and AI-Paraphrased Social Text

arXiv:2608.15338v1 Announce Type: new Abstract: Sentiment classifiers are increasingly applied to social media content that is either sarcastic or AI-generated --- two distributional regimes where standard evaluations…

NARRATE: A Multimodal Real-World Australian Driving Dataset for Human-Centred Explanations in Automated Driving

arXiv:2608.14767v1 Announce Type: cross Abstract: Automated vehicles must explain their decisions in ways that passengers can understand, monitor, and trust. Existing language-annotated driving datasets are mostly…

When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory

arXiv:2608.12888v2 Announce Type: replace Abstract: Agent-memory systems increasingly buy retrieval quality with structure, transforming raw conversation histories into summaries, embeddings, trees, or knowledge graphs…

I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering

arXiv:2604.03904v2 Announce Type: replace Abstract: Large language models (LLMs) often produce confident but incorrect answers, in part because standard evaluation incentives reward guessing over expressing uncertainty.…

AutoMem: A Text-Gradient Recursive Self-Improvement Framework for Automated Memory Architectures Search

arXiv:2608.14621v1 Announce Type: new Abstract: Long-term memory is increasingly central to LLM agents, yet memory design remains a highly coupled architecture problem: what to encode, how to store it, how to retrieve…

The Political Ideology of Large Language Models: Measurement, Inconsistency, and Persuasive Influence

arXiv:2505.04171v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are a transformational technology, fundamentally changing how people obtain information and interact with the world. As people…

jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers

arXiv:2605.08384v4 Announce Type: replace Abstract: In this work, we introduce GELATO (Geometry-preserving Embeddings via Locked Aligned TOwers), a novel approach to multimodal embedding models. We build on the…

Leakage-Audited Benchmarking Reveals Limited Evidence for Cross-Subject Auditory-Evoked EEG Vowel Perception Decoding

arXiv:2605.00865v3 Announce Type: replace-cross Abstract: We tested whether auditory-evoked EEG supports subject-independent five-vowel perception decoding when trial identity, model identity, prediction provenance, and…

QA-Merging: Query-Adaptive Reasoning via Layer Selective Model Merging

arXiv:2601.03506v2 Announce Type: replace Abstract: Recent large reasoning models (LRMs) have achieved strong performance on complex reasoning tasks by generating a long chain-of-thought (Long-CoT). However, such…

Agentic Test-Time Scaling for WebAgents

arXiv:2602.12276v2 Announce Type: replace-cross Abstract: Test-time scaling has become a standard way to improve performance and boost reliability of neural network models. However, its behavior on agentic, multi-step…

Where Does Retrieval Fail? Evaluating RAG Architectures for Agricultural Advisory

arXiv:2608.14886v1 Announce Type: new Abstract: Retrieval quality in RAG systems is commonly reported as a single aggregate score, which can hide large differences across query types and language conditions. We study…

A Large-Scale Chinese Knowledge Graph-Text Alignment Dataset for Benchmarking Knowledge-Grounded LLMs

arXiv:2510.06039v2 Announce Type: replace Abstract: Reliable evaluation of knowledge-grounded Large Language Models (LLMs) in Chinese requires resources that explicitly align Chinese-language text with verifiable…

Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies

arXiv:2608.16645v1 Announce Type: cross Abstract: Can a language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography? We introduce Reconstruction, a blind…

ContextClaim: A Context-Driven Paradigm for Verifiable Claim Detection

arXiv:2603.30025v2 Announce Type: replace Abstract: Automated fact-checking pipelines typically begin with a filtering stage that decides which claims are worth verifying, given that the later evidence retrieval and…

Lost in Adaptation: Layer-Selective Recovery of Temporal Reasoning in Video-Language Models

arXiv:2604.11399v2 Announce Type: replace-cross Abstract: Multimodal adaptation can erode temporal reasoning (TR) in video-language models (VLMs), leaving models able to perceive salient events yet unable to infer their…

Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents

arXiv:2608.14606v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as synthetic survey respondents, but existing evaluations ask whether answers look plausible at the individual level.…

Structural Generalization on SLOG without Hand-Written Rules

arXiv:2604.26157v4 Announce Type: replace Abstract: Structural generalization in semantic parsing requires systems to apply learned compositional rules to novel structural combinations. Existing approaches either rely…

Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans

arXiv:2608.16514v1 Announce Type: cross Abstract: Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath. Whether multimodal large language models (MLLMs),…

CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation

arXiv:2608.13387v2 Announce Type: replace Abstract: On-policy distillation (OPD) supervises a student language model on trajectories sampled from its current policy, but assigns equal credit to response tokens with…

Logical Embeddings for Argument Analysis

arXiv:2608.15325v1 Announce Type: new Abstract: We propose a new framework for machine-learning-oriented argument analysis tasks. Our proposal involves replacing traditional contextualized word embeddings used in most…

Single-Round Vector RAG vs an LLM-Compiled Wiki: A Preregistered Comparison on a Small Multi-Domain Research Corpus

arXiv:2605.18490v2 Announce Type: replace Abstract: We preregistered a comparison of two ways to help an LLM answer questions over a small research corpus: a single-round Vector RAG system and an LLM-compiled markdown…

Subliminal Steering: Stronger Encoding of Hidden Signals

arXiv:2604.25783v2 Announce Type: replace Abstract: Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model.…

DanceOPD: On-Policy Generative Field Distillation

arXiv:2606.27377v3 Announce Type: replace-cross Abstract: Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing. However,…

Semantic Lenia: Emergence of Homeostatic Solitons within the Semantic Space of Large Language Models

arXiv:2608.11657v2 Announce Type: replace Abstract: We introduce Semantic Lenia, an artificial life framework that transforms Large Language Model (LLM) inference from a static optimization problem into a continuous,…

Sequential LLM Release Facilitates Manipulation in Regulated Markets

arXiv:2601.11496v3 Announce Type: replace-cross Abstract: AI agents increasingly mediate bargaining, negotiation and persuasion for people and firms. Such markets extend software-mediated commerce, but add a governance…

Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignment

arXiv:2508.07195v2 Announce Type: replace Abstract: Recent advances have demonstrated that Large Language Models (LLMs) can be effectively adapted for time series forecasting, revealing strong potential beyond natural…

VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?

arXiv:2608.10875v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mostly use short, self-contained requests in static…

Evidence of conceptual mastery in the application of rules by Large Language Models

arXiv:2503.00992v2 Announce Type: replace-cross Abstract: In this paper we leverage psychological methods to investigate LLMs' conceptual mastery in applying rules. We introduce a novel procedure to match the diversity…

TRACE-BN: Transferring Bangla-English Tutoring Behavior to a Sub-1B Offline Language Model

arXiv:2608.15223v1 Announce Type: new Abstract: Bangla-English tutoring requires more than producing a correct translation: learners also need explanations of grammar differences, awareness of their likely errors, and…

$R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets

arXiv:2608.16033v1 Announce Type: new Abstract: In cognitive science, resource rationality asks how an agent should allocate limited computation to maximize expected value. Most reasoning and agent benchmarks use…

Large Language Model Assisted Operational Monitoring for Battery Energy Storage System Integrated Power Distribution Networks

arXiv:2608.15396v1 Announce Type: cross Abstract: Battery energy storage systems (BESS) are increasingly used in distribution networks for voltage regulation and demand response, which increases the volume and…

Aborted but Not Forgotten: KV-Cache Retention Breaks Rollback Consistency in Language Agents

arXiv:2608.15939v1 Announce Type: new Abstract: Stateful language agents assume a rejected branch can be taken back by clearing it from the application transcript. We show this breaks when the serving session retains…

Automatic or Controlled? Repetition Priming Reveals Divergent Processing in Base LLMs, Instruct LLMs, and Humans

arXiv:2608.14681v1 Announce Type: new Abstract: Words recur constantly in natural language use, yet it remains unclear whether language models reactivate prior representations or re-evaluate repeated words afresh, and…

How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks

arXiv:2608.14905v1 Announce Type: new Abstract: AI has long assisted scientific research, but the rapid advance of LLMs and agentic scaffolds is reshaping the landscape; a single system can now carry whole-stage…

Policy Iteration with Human Feedback: Bringing Post-Training RL to In-context Learning

arXiv:2608.16831v1 Announce Type: cross Abstract: Generative pretraining established reusable task representations; later work on language-based task conditioning and in-context learning showed that a fixed model could…

Beyond the pale: Assessing prevalence and contents of extremist speech in LLM training data

arXiv:2608.14813v1 Announce Type: new Abstract: Despite a strong interest on the part of the research community in the topic of trustworthy and safe AI, the composition of the text corpora that large language models…

Characterizing Rhetorical Misalignment in Decision-Making with Language Models

arXiv:2608.14630v1 Announce Type: new Abstract: Human decision-making is often shaped by a range of well-documented cognitive biases. As large language models (LLMs) become increasingly integrated into high-stakes…

Multi-Modal Generative Fuzzy System: Fuzzy Inference Guided Large Model Interactive Question Answering Framework

arXiv:2608.14584v1 Announce Type: new Abstract: In Multimodal Question Answering (MQA), models are required to jointly encode and integrate heterogeneous information from multiple modalities, including text, images, and…

AWED-PIPER: Agents, Web Applications & Expert Detectors for Personally Identifiable Information Protection & Fine-grained Named Entity Recognition across 36 languages for 6.6 Billion Speakers

arXiv:2601.10161v3 Announce Type: replace Abstract: Named Entity Recognition (NER) and Personally Identifiable Information (PII) anonymization are critical tasks in Natural Language Processing (NLP) for information…

The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context

arXiv:2608.14838v1 Announce Type: cross Abstract: Retrieval components for code assistants are tuned against retrieval metrics: a configuration that raises recall@k is adopted, and downstream task success is assumed to…

Trust Is Not Enough: Influence Calibration for On-Policy Self-Distillation in Agentic RL

arXiv:2608.14945v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) gives language agents dense token-level supervision from a privileged self-teacher on the policy's own trajectories. Existing methods…

Scaling Manual-Grounded Appliance Manipulation with Data Synthesis and Unified Planning

arXiv:2608.15863v1 Announce Type: cross Abstract: Operating household appliances requires long-horizon planning that is state-dependent and robust to disturbances, yet existing large models fall short, as no…

Language Models Compare Quantities Using Number-specific and Unit-specific Heuristics

arXiv:2606.03982v2 Announce Type: replace Abstract: Quantities with measurement units, such as 110 cm and 1.2 m, require language models (LMs) to combine a numeral with a symbolic unit scale. Here, we study how LMs…

Train Yourself as an LLM: Exploring Effects of AI Literacy on Persuasion via Role-playing LLM Training

arXiv:2604.02637v2 Announce Type: replace Abstract: As large language models (LLMs) become increasingly persuasive, there is concern that people's opinions and decisions may be influenced across various contexts at…

QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents

arXiv:2608.16168v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly use external memory systems to support personalization by drawing on long and evolving interaction histories, in which user…

MechMath: Sorrifier-Driven Formal Decomposition Workflow for Automated Theorem Proving

arXiv:2603.24465v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) and LLM-based agents have substantially improved the capabilities of automated theorem proving. However, for problems…

Dense Expands, Sparse Anchors: Channel-Asymmetric Query Expansion for Hybrid Retrieval

arXiv:2608.15851v1 Announce Type: cross Abstract: LLM-based query expansion improves retrieval by generating document-like passages. In hybrid retrieval, however, most evaluations fuse fixed top-$L$ dense and sparse…

What to Forget in Unlearning? Forget Set Curation for Language Models

arXiv:2608.14855v1 Announce Type: new Abstract: Machine unlearning aims to remove targeted data or behaviors from a trained model without retraining from scratch. Yet most evaluations assume that the examples to forget…

Does generative AI supersede supervised XMLC? A Benchmark Study on Automated Subject Indexing with German Scientific Literature

arXiv:2607.14882v2 Announce Type: replace-cross Abstract: With a large controlled vocabulary as the label set, the task of automated subject indexing in a library can be understood as a multi-label classification task.…

ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models

arXiv:2605.23694v3 Announce Type: replace Abstract: Chart descriptions are essential for accessibility, cross-modal retrieval, and assisting readers in extracting insights from complex visualizations. As multimodal…

Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models

arXiv:2608.15129v1 Announce Type: new Abstract: We systematically compare word order preferences in decoder-only language models across 192 artificial languages and typologically diverse natural languages. On artificial…

Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns

arXiv:2607.11621v2 Announce Type: replace-cross Abstract: Aphasia following stroke commonly produces systematic naming errors with characteristic profiles, but whether general-purpose language models not designed for…

DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning

arXiv:2502.11603v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit strong natural language understanding capabilities but also inherit and amplify societal biases, particularly gender bias, raising…

Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents

arXiv:2608.15008v1 Announce Type: new Abstract: Memory is becoming core infrastructure for long-horizon LLM agents, yet existing evaluations offer limited guidance on which memory substrate, namely the underlying medium…

LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking

arXiv:2506.07449v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have driven their adoption in recommender systems through Retrieval-Augmented Generation (RAG) frameworks.…

IndicQE-APE: A Benchmark for Quality Estimation and Automatic Post-Editing for Indic Languages

arXiv:2608.16344v1 Announce Type: new Abstract: Indic quality estimation (QE) and automatic post-editing (APE) data is spread across separate releases, so no single resource supports training and evaluation across tasks…

Misconception Diagnosis From Student-Tutor Dialogue: Generate, Retrieve, Rerank

arXiv:2602.02414v2 Announce Type: replace Abstract: Timely and accurate identification of student misconceptions is key to improving learning outcomes and pre-empting the compounding of student errors. However, this…

When Less Is Enough: Context Selection and Prompting Strategies for Bengali News Headline Generation

arXiv:2608.15879v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong performance in text generation tasks, yet their effectiveness on headline generation remains sensitive to how input context…

A Comprehensive Survey of Wireless Foundation Models for AI-Native 6G Networks

arXiv:2608.14694v1 Announce Type: new Abstract: Foundation models are emerging as a transformative paradigm for AI-native sixth-generation (6G) wireless networks by enabling scalable, transferable, and data-efficient…

Grounding Healthcare LLMs in a Causal Knowledge Graph: Framework, Metrics, and a Cardiovascular Pilot

arXiv:2608.15382v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly proposed for healthcare decision support, but their evaluations still reward single-answer accuracy rather than reasoning…

Agent Inheritance Protocol: Speculating on Feralized Agents After Principals Die

arXiv:2608.15403v1 Announce Type: cross Abstract: You will die eventually. Your agents may not. An AI agent operating on decentralized blockchain infrastructure has no concept of death; it can only go bankrupt -- frozen…

Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models

arXiv:2608.16805v1 Announce Type: cross Abstract: Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Generic…

NumerosityVLM: A Cognitively Inspired Benchmark for Interpreting Numerosity Representations in Vision-Language Models

arXiv:2608.15425v1 Announce Type: cross Abstract: Vision-language models (VLMs) achieve strong performance on high-level multimodal tasks, yet numerosity perception, a cognitive ability that emerges in human infants…

ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Edits

arXiv:2608.15138v1 Announce Type: new Abstract: Designing an ABR algorithm for one network scenario takes an engineer months, and large language models now do this work in hours, matching or beating hand-built designs.…

Position: AI Lock-In Is in Progress, and We Must Be Prepared

arXiv:2608.14565v1 Announce Type: new Abstract: AI safety research has mainly focused on two areas: technical alignment (ensuring AI systems produce human-aligned outputs) and the regulation of generative AI's societal…

Generative data assimilation highlights fronts as key regulators of ocean energy cascade

arXiv:2608.14955v1 Announce Type: cross Abstract: Mesoscale eddies are fundamental to the ocean circulation, yet the extent to which submesoscale motions, a few kilometers across, influence mesoscale eddy energetics…

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

arXiv:2608.15127v1 Announce Type: cross Abstract: Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state.…

Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis

arXiv:2608.16775v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly being deployed in cybersecurity operations to assist cybersecurity analysts with rapid decision-making against emerging…

Audio-Visual Segmentation via Depth-Guided Collaborative Modeling

arXiv:2608.16285v1 Announce Type: cross Abstract: Audio-Visual Segmentation (AVS) is a fundamental task in multimodal perception that performs pixel-level segmentation of sounding objects in videos by leveraging both…

OTel: Building Domain-Specialized Telecom LLM Foundations for Intelligent Networks

arXiv:2608.15436v1 Announce Type: new Abstract: Frontier AI models have advanced rapidly, but they still struggle with telecom-specific tasks. We present Open Telco (OTel), an open telecom AI resource with derived…

Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain

arXiv:2608.16164v1 Announce Type: new Abstract: Training locomotion policies for complex unstructured terrain requires a curriculum to avoid early exploration failures. However, since unstructured terrain lacks explicit…

ALPS: Measuring Valid Creativity in Large Language Models with Mathematical Construction

arXiv:2608.15979v1 Announce Type: new Abstract: Large language models produce outputs presented as discoveries - new proofs, conjectures, or molecules. Whether such an output that appears creative is truly original and…

When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning

arXiv:2608.14610v1 Announce Type: new Abstract: Legal reasoning tasks such as legal judgment prediction (LJP) require identifying the temporally correct version of the law governing a case -- a capability we term…

Agent-Native Telemetry: Verifiable State-Delta Evidence for Autonomous Operations

arXiv:2608.16178v1 Announce Type: cross Abstract: Operational telemetry is predominantly engineered for human reading: systems repeatedly serialize verbose prose, static keys, and redundant context across billions of…

Validation-Frontier Representation Selection under Constrained Observation

arXiv:2608.15095v1 Announce Type: new Abstract: AI systems deployed outside clean benchmark settings often rely on observations that are incomplete, unstable, costly, or degraded by monitoring failures. This paper…

Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication

arXiv:2608.16192v1 Announce Type: new Abstract: Generative visual-token communication reduces transmission load by sending only selected discrete tokens and reconstructing missing content at the receiver. However,…

THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts

arXiv:2608.15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure. Existing activation steering methods…

AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research

arXiv:2608.11216v2 Announce Type: replace Abstract: World modeling is an unsettled field: architectures, training objectives, and state representations interact in complex ways, and no single recipe dominates across…

CEDAR-GRPO: Process-Aware Reinforcement Learning for General Abductive Reasoning in LLMs

arXiv:2608.14791v1 Announce Type: new Abstract: Abductive reasoning, often characterized as inference to the best explanation, is central to explanation under uncertainty, from everyday sense-making and investigation to…

When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding

arXiv:2608.16801v1 Announce Type: new Abstract: We study how teams of AI coding agents coordinate while solving programming tasks. Current evaluations usually report whether the agents complete the task and how much the…

Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference

arXiv:2608.15016v1 Announce Type: cross Abstract: Network incident response remains slow and labor-intensive as the defender must infer multi-stage attacks from partial observations and translate recovery decisions into…

TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation

arXiv:2608.15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass…

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

arXiv:2608.15930v1 Announce Type: new Abstract: Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution.…

SIGMA-Lane: Scale-pyramId Gated MAmba for Temporally Consistent Video Lane Detection

arXiv:2608.16338v1 Announce Type: cross Abstract: Video lane detection requires predictions that remain stable across frames, yet severe vehicle occlusions can break temporal cues. In streaming recurrent models,…

A Temporal Planning Framework for Disruption Aware Dynamic Route Optimization in Heterogeneous Railway Systems

arXiv:2606.14582v2 Announce Type: replace Abstract: Efficient route optimization play a vital role in ensuring both safety and punctuality in railway operations. It is very crucial particularly in heterogeneous…

HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL

arXiv:2608.16837v1 Announce Type: cross Abstract: Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not…

Constitutive Priors for Machine Intelligence: A Legitimacy Theory of the Artificial Physical World

arXiv:2608.15147v1 Announce Type: new Abstract: Machine intelligence has conquered the symbolic world but stalled at the physical one. The stall is structural: physical AI faces a cold-start deadlock -- no intelligence…

Constraint-Aware Synthetic Tabular Data Generation via Inter-Column Constraint Discovery with LLM Agents

arXiv:2608.15109v1 Announce Type: new Abstract: Generating structurally valid synthetic tabular data remains difficult: outputs with high statistical fidelity and downstream utility can still violate semantically…

A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognition

arXiv:2608.15160v1 Announce Type: cross Abstract: Automatic modulation recognition (AMR) faces distinct representation bottlenecks under varying observation lengths, where a single model architecture often fails to…

An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use Case

arXiv:2608.14587v1 Announce Type: new Abstract: Background: Recent advances in information retrieval (IR) leverage both dense and sparse representations, large language models (LLMs), and specialized retrieval models to…

OGX: An Open-Source, Vendor-Neutral Generative AI Application Server

arXiv:2608.14580v1 Announce Type: new Abstract: OGX (Open GenAI Stack) is an open-source AI application server and Python library that implements the APIs of major frontier labs (OpenAI, Anthropic, Google) with…

When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction

arXiv:2608.15592v1 Announce Type: new Abstract: Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput. Predicting output…

When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation

arXiv:2608.14940v1 Announce Type: new Abstract: Current agent evaluations score models on the state visible at the end of a stopped run which they count as one trial. However, interpreting the score as a final result…

From Reactive to Autonomous: Evolution of AI Operations in Cloud Network Infrastructure

arXiv:2608.14574v1 Announce Type: cross Abstract: The operational model for cloud network infrastructure has undergone a fundamental transformation over the past decade. What began as manual, human-driven…

Large Language Models and their Awareness of Mechanics and Spatial Geometry

arXiv:2608.14615v1 Announce Type: new Abstract: Large Language Models (LLMs) perform well on established code-generation and mathematical-reasoning benchmarks, but their capabilities in mechanics and spatial geometry,…

SpIn-ViT: Designing a Sparsity-Induced Vision Transformer That Is Mechanistically Interpretable

arXiv:2608.14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools to decompose…

Augmenting Text to Increase Translation Difficulty

arXiv:2608.15932v1 Announce Type: new Abstract: As state-of-the-art machine translation models saturate standard benchmarks, the field needs more challenging evaluations to distinguish between models of varying quality.…

Software Engineering for AI-driven Building Operation

arXiv:2608.16237v1 Announce Type: cross Abstract: Building operations are energy-inefficient. Artificial Intelligence (AI)-driven control systems promise benefits through optimization and predictive control, but…

AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems

arXiv:2608.16381v1 Announce Type: new Abstract: Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many calls and stages. We…

Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL

arXiv:2608.15389v1 Announce Type: new Abstract: LLM-based Text-to-SQL progress is reported across heterogeneous benchmarks, backbones, and inference protocols, making cross-system comparison fragile. We reframe the…

Adaptive Mixing of Policies from Searching and Policies from Learning

arXiv:2608.15700v1 Announce Type: new Abstract: Background: Distillation of training targets generated thru search/planning has proven useful in reinforcement learning, but search can take exceedingly long. Objectives:…

Local AI pre-screening for human triple-blind peer review in health sciences

arXiv:2608.14625v1 Announce Type: cross Abstract: Academic peer review is under mounting strain: NeurIPS 2025 received 21,575 submissions, ICLR 2025 received 11,603, and ICML 2025 received 12,107. This volume has…

Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation

arXiv:2608.15877v1 Announce Type: new Abstract: Search and recommendation serve a shared discovery objective but encode intent differently. We study this boundary through Dear Algo on Threads, a deployed product where…

MUPA$^{2}$E: Multimodal Unified Perception with Asymmetric Attention for Emotion Assessment

arXiv:2608.15999v1 Announce Type: new Abstract: Automatic emotion assessment can benefit from combining neural and behavioral signals, but many multimodal approaches rely on separate, modality-specific…

EA-LiteUNet: An Edge-Adaptive and Resource-Efficient U-Net for Boundary-Sensitive Dermoscopic Image Segmentation

arXiv:2608.15537v1 Announce Type: cross Abstract: Accurate boundary delineation remains a persistent challenge in dermoscopic image segmentation because of blurred lesion margins, heterogeneous textures, and complex…

Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems

arXiv:2608.14667v1 Announce Type: new Abstract: Large language model-based agents are increasingly deployed as collaborators in scientific discovery yet most current work focuses on the autonomous capabilities of "AI…

FZ-VLM: A Two Stage Florence-Zephyr Vision Language Model Framework for Pulmonary Nodule Characterization and Clinical Decision Making

arXiv:2608.15004v1 Announce Type: cross Abstract: Lung cancer remains one of the leading causes of cancer-related mortality worldwide, and Computed Tomography (CT) is a primary imaging tool for screening and followup…

MELD: A Protocol for Merging Knowledge Across Distributed Agentic Memories

arXiv:2608.16357v1 Announce Type: cross Abstract: Autonomous agents share a transport and can call each other's tools, but they cannot share what they know: no protocol lets two agents' memories reconcile a fact phrased…

Beyond Direct Access: Resource Hijacking in LLM Agents

arXiv:2608.15108v1 Announce Type: cross Abstract: Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identities, private…

BRA-Audit: Budgeted Runtime Auditing for LLM Multi-Agent Systems via Cumulative-Exposure Audit-Point Placement

arXiv:2608.14668v1 Announce Type: cross Abstract: LLM-based multi-agent systems (LLM-MAS) solve complex tasks through specialized collaboration, but inter-agent dependencies can propagate hallucinated or malicious…

Multi-Agent Closed-Loop Reasoning for Organic Structure Elucidation from Multimodal Spectra

arXiv:2608.14720v1 Announce Type: cross Abstract: Following the molecular discovery and synthesis revolutions, scalable automated structure elucidation from routine spectroscopic data remains an outstanding challenge.…

CETalk: Continuous Valence-Arousal Control for Audio-Driven 3D Talking Head Generation

arXiv:2608.15110v1 Announce Type: cross Abstract: Emotional 3D talking head generation aims to synthesize expressive facial animations with accurate lip synchronization. However, existing methods often rely on discrete…

Decoupling Parcellation from Classification: Systematic Benchmark of Fast Brain Segmentation Methods for Alzheimer's Disease Detection

arXiv:2608.16039v1 Announce Type: cross Abstract: Brain parcellation and classification are typically evaluated in isolation, yet downstream AD detection performance depends on their interaction. We decouple these…

Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents

arXiv:2608.16578v1 Announce Type: new Abstract: AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can…

RISE: Roadside Infrastructure Sequence Understanding across 3D Tracking and Structured Vision-Language Reasoning

arXiv:2608.16480v1 Announce Type: cross Abstract: We present RISE (Roadside Infrastructure Sequence Understanding and Evaluation), a framework spanning metric 3D tracking and structured vision-language reasoning in…

Chameleon: An Adaptive AI-Driven Honeypot Architecture Using Threat-Calibrated Particle Swarm Optimization and Semantic Deception Rapidly-Exploring Random Trees

arXiv:2608.15407v1 Announce Type: cross Abstract: An invariant behavioral profile is the defining vulnerability of traditional honeypot installations: a skilled adversary can confirm the presence of a deception…

Beyond Correctness: Toward Automated Novelty Verification with Lean 4

arXiv:2608.14669v1 Announce Type: new Abstract: Artificial intelligence systems applied to mathematics verify correctness but not novelty: an automatically generated theorem can compile in Lean without errors and yet be…

Beyond Pass@k: Measuring Reliability and Security of Agentic Code Generation

arXiv:2608.14711v1 Announce Type: new Abstract: AI coding agent benchmarks rank agents with the Chen et al. (2021) pass@k estimator, but current implementations misapply it: they set n to the number of unit tests in a…

Mental Model Management: An Operator-Based Framework for LLM Memory

arXiv:2608.15451v1 Announce Type: new Abstract: Large language models process large amounts of information but usually lack an explicit mechanism for maintaining compact and evolving conceptual representations. We…

GoalEvolve: From Handcrafted Algorithm Priors to Goal-Driven Evolution of Physical Design Algorithms

arXiv:2608.16733v1 Announce Type: cross Abstract: Physical design algorithms operate within tightly coupled, multi-stage optimization flows, where stage-local gains may vanish or induce downstream degradation. Existing…

Large language models as synthetic clinical experts to inform longitudinal rare-disease modeling

arXiv:2608.16507v1 Announce Type: new Abstract: Due to the limited amount of information, modeling longitudinal rare-disease data can benefit from integrating clinical knowledge. Yet, elicitation of expert knowledge and…

SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling

arXiv:2508.09105v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and contextual understanding…

Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps

arXiv:2608.16309v1 Announce Type: cross Abstract: Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipeline, leaving it…

GRIP: Grounded Reasoning via Information-Restricted Premises

arXiv:2608.16776v1 Announce Type: new Abstract: High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irrelevant. We call…

MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems

arXiv:2608.15006v1 Announce Type: cross Abstract: Although visual reasoning is crucial for solving complex geometry tasks, existing vision-language models rely heavily on text-only reasoning. Some recent methods…

Euclid-Omni : A Unified Neuro-Symbolic Framework for Plane Geometry

arXiv:2608.14585v1 Announce Type: new Abstract: Euclidean geometry is a compelling testbed for AI reasoning, as it demands the combination of intuitive diagram understanding, axiomatic deduction, and algebraic…

The Quality of Claude AI-authored Python Tests Is Not Weaker Than Human-authored Tests

arXiv:2608.15188v1 Announce Type: cross Abstract: We evaluate the quality of Claude AI-written Python tests against human-written Python tests from two established open-source projects Django and Pandas. Hundreds of…

HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object-Interaction

arXiv:2608.16222v1 Announce Type: cross Abstract: Humanoid intelligence requires learning over an extremely diverse space of whole-body motions and physically grounded interactions. However, existing embodied datasets…

Platform Adaptation Under Governance Interventions: Actor Best-Response Modeling and an External Public-Case Benchmark

arXiv:2608.15131v1 Announce Type: new Abstract: Digital platforms govern by changing rules: rankings, monetization thresholds, moderation standards, verification systems, disclosure requirements, appeal processes, and…

TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation

arXiv:2608.16765v1 Announce Type: cross Abstract: Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task types (e.g.,…

The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents

arXiv:2603.00801v2 Announce Type: replace Abstract: Language agents increasingly act as web-enabled systems that search, browse, and synthesize information from diverse sources. However, these sources can include…

A cross-modal generative model for incomplete and degraded prostate MRI with multicentre clinical validation

arXiv:2608.16233v1 Announce Type: cross Abstract: Missing or degraded sequences can limit prostate multiparametric MRI. We developed MSCNet, a sequence-conditioned cross-modal generative framework for reconstructing…

EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints

arXiv:2608.15502v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising foundation for Embodied AI, but their high inference cost poses significant challenges for deployment in…

MoE Router-Guided Clustering for Heterogeneous Federated Instruction Tuning

arXiv:2608.15311v1 Announce Type: new Abstract: Federated instruction fine-tuning enables Large Language Models (LLMs) to adapt to decentralized, privacy-sensitive data without requiring data sharing. Recent…

Unsupervised Anomaly Detection for Image Dataset Quality Assurance in Multi-Center Breast MRI

arXiv:2608.16725v1 Announce Type: cross Abstract: Corrupted, inconsistent, or anomalous data silently threatens the safety and reliability of medical AI. Despite growing regulatory recognition of dataset quality…

Translating finite-domain integer constraint models to CP/SMT/ILP/PB/SAT solvers with CPMpy

arXiv:2608.15143v1 Announce Type: new Abstract: Constraint solving is a declarative approach for solving combinatorial satisfaction and optimization problems. The user specifies their problem through constraints and…

Understanding Cognition-Induced Risks in Agentic AI Systems

arXiv:2608.15304v1 Announce Type: new Abstract: Frontier agentic systems powered by large language models (LLMs) exhibit human-like patterns of cognition. As these systems become deeply integrated across different…

Large Language Models Show Metacognitive Sensitivity in Medical Reasoning

arXiv:2608.14552v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated and used in medicine, but clinical usefulness depends on answer accuracy and whether confidence tracks evidence…

Calibrated Generative AI as Meta-Reviewer: A Systemic Functional Linguistics Discourse Analysis of Reviews of Peer Reviews

arXiv:2509.15035v2 Announce Type: replace Abstract: This study investigates the use of generative AI to support formative assessment through machine generated reviews of peer reviews in graduate online courses in a…

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

arXiv:2604.06628v2 Announce Type: replace Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for…

Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs

arXiv:2608.14765v1 Announce Type: new Abstract: Data cleaning without a trusted clean reference is challenging because unusual values may represent either genuine errors or valid observations. This paper studies how…

Does the Proof Prove It That Way? Faithful Formalization of Elements Proofs

arXiv:2608.15432v1 Announce Type: new Abstract: In formal verification, both the autoformalization of statements and automated proof search have been studied extensively. While automated proof search can produce a…

Toward AI-Friendly Cartography: Understanding How Color Design Influences Foundation Model Spatial Reasoning on Sequential Choropleth Maps

arXiv:2608.15736v1 Announce Type: new Abstract: Foundation models (FMs) increasingly support multimodal and geospatial reasoning, yet it remains unclear whether cartographic principles designed for human perception are…

X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization

arXiv:2608.16658v1 Announce Type: cross Abstract: Cross-view Video Geo-localization (CVG) aims to localize ground-view videos by retrieving their corresponding geo-tagged aerial images. However, CVG approaches rely on…

Quipu: A Governed Bitemporal Knowledge Graph Store

arXiv:2608.16813v1 Announce Type: new Abstract: Agents now write knowledge graphs, but knowledge-graph stores still carry defaults set when humans curated them: accept writes now and clean later, keep one time axis or…

Artificial Intelligence as a Tool for Combating Child Labour: A Real-Time Edge Vision Pipeline for Child Detection and Age Estimation

arXiv:2608.14770v1 Announce Type: cross Abstract: An estimated 138 million children remain in child labour worldwide, and the monitoring systems used by affected sectors, built on periodic household visits and…

Budget-Aware Tool Use Enables Effective Agent Scaling

arXiv:2511.17006v2 Announce Type: replace Abstract: Scaling test-time computation has been extended from language model reasoning to tool-augmented agents, where scaling involves not only thinking in tokens but also…

Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs

arXiv:2608.16391v1 Announce Type: cross Abstract: As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the ecosystem. Auditing…

Visualizing Uncertainty-to-Action Composition for Human Oversight

arXiv:2608.16428v1 Announce Type: cross Abstract: Artificial intelligence systems often disclose uncertainty, yet they rarely make clear what response that uncertainty should trigger. Most uncertainty visualizations…

The Benchmark Trap: Structures of Power and Injustice in AI Evaluations

arXiv:2608.15326v1 Announce Type: new Abstract: Artificial intelligence (AI) benchmarks are not neutral tools of evaluation but socio-technical artefacts that shape competition, power, and research priorities within AI.…

Synthetic Data Augmentation for Satellite-Based Analysis of Battle-Damaged Agricultural Fields in Ukraine

arXiv:2608.16380v1 Announce Type: cross Abstract: Monitoring war-induced damage to agricultural land in Ukraine is important for understanding threats to food security, environmental stability, and post-war recovery.…

Runtime Observability for Heterogeneous Attention Memory

arXiv:2608.05863v2 Announce Type: replace Abstract: Modern models no longer keep a plain KV cache: latent caches, learned sparse selectors and recurrent states each carry the model's memory in a different form, and each…

Defake-o3: From Speculative Rationales to Verifiable Evidence for Explainable AIGI Detection

arXiv:2608.16259v1 Announce Type: cross Abstract: The rapid progress of image generation models calls for AI-generated image (AIGI) detectors that are not only accurate but also explainable and reliable. While…

Extend the Safety Horizon for Intelligent Transportation Systems through Semantic-Aware Cooperative Perception

arXiv:2608.14603v1 Announce Type: cross Abstract: Cooperative perception enables vehicles and infrastructure to exchange sensor data via Vehicle-to-Everything (V2X) communication, extending sensing coverage beyond…

Divergent-Convergent Reasoning: Scaling Test-Time Compute through Structured Solution Synthesis

arXiv:2608.15303v1 Announce Type: new Abstract: Test-time compute can substantially improve Large Language Model (LLM) reasoning performance, yet how and when additional compute helps remains poorly understood. We study…

Position: Want Better ML Reviews? Stop Asking Nicely and Start Incentivizing with a Credit System

arXiv:2608.14571v1 Announce Type: new Abstract: With soaring submission counts, stricter reciprocal review policies, widespread adoption of platforms like OpenReview, and without the offsetting pressure of publication…

Incoherent by Design? On the Moral Self-Consistency of LLMs

arXiv:2608.15354v1 Announce Type: new Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations. A model that can state a…

Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair

arXiv:2608.15579v1 Announce Type: cross Abstract: Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long horizons, tool-use…

Visible Reasoning and Indirect Prompt-Injection Monitorability Across English, Tamil, and Tanglish

arXiv:2608.15392v1 Announce Type: new Abstract: Chain-of-thought monitoring is a potentially useful safety signal, but its reliability across languages and behavioral settings remains uncertain. In a small case study of…

Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures

arXiv:2608.14586v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult…

LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset

arXiv:2608.15175v1 Announce Type: cross Abstract: Uncrewed aerial vehicles (UAVs) are increasingly deployed for autonomous navigation in complex outdoor environments, where dynamic conditions and mission requirements…

Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm

arXiv:2608.16177v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that operate equipment, execute instructions, and act inside institutional hierarchies, raising a…

HaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents

arXiv:2608.16447v1 Announce Type: new Abstract: Long-horizon embodied tasks require LLM agents to iteratively decompose high-level goals, revise plans in response to environmental feedback, and ground leaf-level…

Information-Theoretic Causal Modelling of Semiconductor Process Dynamics

arXiv:2608.14678v1 Announce Type: cross Abstract: With the progress of the semiconductor industry toward increasingly complex compute devices and tighter process tolerances, advanced process control has become crucial.…

HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes

arXiv:2608.16622v1 Announce Type: cross Abstract: Multimodal harmful meme detection is typically formulated as image--text harmfulness classification. A model may correctly predict harmfulness while misidentifying the…

Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback

arXiv:2608.15591v1 Announce Type: new Abstract: Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, while the business…

Decomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and Decay

arXiv:2608.15780v1 Announce Type: cross Abstract: Stale recommendations are a pervasive challenge and a leading source of user complaints on large-scale content platforms. Items lose relevance through two primary…

CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills

arXiv:2608.16246v1 Announce Type: cross Abstract: Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict for each skill and…

Small Models Scout Bottleneck Order for Large-Model Data Control

arXiv:2608.14936v1 Announce Type: new Abstract: Small proxy models are commonly used to identify data mixtures for larger-scale training. We ask whether their training trajectories reveal another transferable structure:…

Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents

arXiv:2608.15755v1 Announce Type: new Abstract: User-centric multi-turn agents must act on an evolving task situation shaped by changing user intents, accumulated tool-grounded facts, missing information, and execution…

Skill Blocks: How Should an Agent Load Its Skill? A Caching-Correct Comparison of Pre-load, On-Demand Tool-Loading, Progressive Disclosure, and Hybrid

arXiv:2608.14943v1 Announce Type: new Abstract: Agent skills are often injected in full on every request, increasing token cost. We compare four content-preserving loading methods: Full, Skill Block, Reference, and…

Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents

arXiv:2608.16666v1 Announce Type: new Abstract: This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents. Inspired by Overcooked, the suite…

From Doyle to AGM: A Survey and an Implementation Roadmap for Belief Change

arXiv:2608.14567v1 Announce Type: new Abstract: This paper presents a targeted narrative review establishing the historical and theoretical foundations for computational belief change implementation. Seeded by Doyle and…

LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing

arXiv:2608.16763v1 Announce Type: new Abstract: Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and…

GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation

arXiv:2608.14986v1 Announce Type: cross Abstract: Long-horizon robotic manipulation fundamentally relies on persistent spatial memory. However, existing 3D memory systems function merely as passive recorders: they store…

AudioTQ: A Data-Oblivious 6-Bit CPU Audio Codec via Randomized Hadamard Rotation and Lloyd-Max Quantization

arXiv:2608.15369v1 Announce Type: cross Abstract: Lossy audio compression algorithms traditionally rely on psychoacoustic modeling and frequency-domain representations (e.g., MP3, AAC, and Opus) to discard information…

RETRACE: Resilience-Guided Trait-Conditioned Craving Estimation from Wearable Physiology in Opioid Use Disorder

arXiv:2608.14947v1 Announce Type: new Abstract: Detecting opioid craving from wearable physiological signals is critical yet difficult, with the potential to support proactive interventions for individuals with opioid…

UC-PSRO: Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum for Game-Theoretic Course-of-Action Generation in Adversarial Swarms

arXiv:2608.15372v1 Announce Type: new Abstract: We study generating game-theoretically optimized Courses of Action (COAs) for a Blue UAS swarm against an adaptive Red adversary in a communication-degraded environment,…

Position: Evaluations of AI Moral Reasoning Still Miss Half of the Picture

arXiv:2608.14566v1 Announce Type: new Abstract: Recent work on evaluating the moral competence of large language models (LLMs) has focused primarily on what we call the moral value problem, i.e., whether model outputs…

Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability

arXiv:2608.15475v1 Announce Type: cross Abstract: Quantized Vision-Language-Action (VLA) models expose a weight-fault surface: Rowhammer-style faults can corrupt deployed INT8 bits. We present the first bit-flip attack…

TAHB: A Comprehensive Benchmark for Text-Attributed Hypergraph Learning

arXiv:2608.15055v1 Announce Type: new Abstract: Hypergraphs effectively model higher-order groupwise relationships beyond pairwise interactions, while pretrained language models (PLMs) and large language models (LLMs)…

S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices

arXiv:2608.15018v1 Announce Type: new Abstract: Deploying large language models (LLMs) for inference on edge devices is challenging due to severe memory and bandwidth constraints. While speculative decoding and…

Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation

arXiv:2608.15680v1 Announce Type: cross Abstract: Vision-language-action (VLA) models improve robotic manipulation but remain vulnerable to compounding errors, scene changes, and off-trajectory states. Reinforcement…

MotionGS-SLAM: Event-Modulated Gaussian Splatting for Motion-Blur Robust SLAM

arXiv:2608.15024v1 Announce Type: cross Abstract: Current Vision-based SLAM systems fail catastrophically when motion blur corrupts the visual input, as they attempt the ill-posed inverse problem of recovering sharp…

NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulation

arXiv:2608.16503v1 Announce Type: cross Abstract: Real-world deployment of Vision-Language-Action (VLA) models is often bottlenecked by efficiency-performance trade-offs, cross-embodiment generalization, and execution…

Physiological World Models for Human State Transitions

arXiv:2608.15309v1 Announce Type: new Abstract: Continuous multimodal sensing now allows human physiology to be observed throughout daily life rather than only during occasional clinical visits. However, most health…

Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching

arXiv:2608.16791v1 Announce Type: cross Abstract: Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security…

ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Models

arXiv:2608.15145v1 Announce Type: new Abstract: Large Language Models (LLMs) have been increasingly adopted in Text-to-SQL systems, yet SQL errors remain a major obstacle in real-world Text-to-SQL inference pipelines.…

GSBF: Gaussian Splatting for Environment-Aware Beamforming

arXiv:2608.05896v2 Announce Type: replace Abstract: Beamforming plays a key role in multiple-input-multiple-output (MIMO) communication systems. However, conventional beamforming design normally requires accurate…

Valhalla: A Layered Knowledge-State and Service-Governance Framework for Long-Term Scientific Knowledge Work

arXiv:2608.15193v1 Announce Type: cross Abstract: As large language model (LLM) agents are increasingly adopted in scientific research, external knowledge bases, knowledge graphs, and long-term memory have improved…

Catching Hallucinated Citations in Video-LLM Question Answering: A Self-Verification Pipeline and Verifier Ablation Study

arXiv:2608.15574v1 Announce Type: cross Abstract: Video question answering systems built on vision-language models often produce timestamped claims with high confidence even when unsupported by the cited frame. This…

Intelligent Base Station Deployment in Urban Wireless Networks: A Geographic Data-Informed Digital Twin Approach

arXiv:2608.14599v1 Announce Type: cross Abstract: The placement of base station (BS) is a fundamental determinant of coverage and capacity of urban wireless networks. Yet large-scale BS deployment optimization remains…

JarvisBench: Always-on Intelligence Between Humans and Agents

arXiv:2608.14870v1 Announce Type: new Abstract: Long-horizon agents can execute continuously, but human attention remains intermittent and scarce. This creates a bidirectional coordination problem: users may need…

Max-Q Selective Imitation for Human-in-the-Loop Online Robot Learning

arXiv:2608.15088v1 Announce Type: cross Abstract: Human-in-the-loop (HIL) online reinforcement learning for real robots must absorb human interventions quickly while continuing to improve beyond the human prior. We…

MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration

arXiv:2601.23049v2 Announce Type: replace Abstract: Medical calculators are fundamental to quantitative, evidence-based clinical practice. However, their real-world use is an adaptive, multi-stage process, requiring…

Process-Constituted Intelligence: A Shared Criterion for Humans and Machines

arXiv:2608.16213v1 Announce Type: new Abstract: Intelligence is constituted by \textit{process} (iterative activity through which output emerges), not in the output itself. Generative AI (GenAI) is trained on…

Bounded Agents: Delegation Security for Multi-Agent AI Systems

arXiv:2608.15888v1 Announce Type: new Abstract: LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents. At session start, the agent's permissions are set but remain static,…

The Value of a Prompt: An LLM-Relative Kolmogorov-Complexity Approach

arXiv:2608.16438v1 Announce Type: new Abstract: In a world where valuable artifacts are increasingly created, completed, or processed by LLMs, the central economic question is not only what the LLM can produce, but what…

The Authority Resolution Framework: A Five-Domain Ontology for Governing Who and What Decides, at Scale

arXiv:2608.15832v1 Announce Type: new Abstract: As AI systems become increasingly capable of autonomous action, determining whether an agent is technically capable of performing an action is insufficient: the system…

Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State

arXiv:2608.15810v1 Announce Type: new Abstract: Runtime compression of serving state trades quality for capacity with no priced guarantee: systems adapt precision on load signals with no soundness statement, and…

The Unwritten Benchmark: A New Challenge for Multimodal Machine Learning in Abstract Perceptual Reasoning

arXiv:2608.14558v1 Announce Type: new Abstract: Current multimodal models have demonstrated remarkable proficiency in recognizing static visual and auditory content. However, their capacity for abstract perceptual…

Time to Reason: Scalable Neurosymbolic Learning for LTLf via Fuzzy Semantics

arXiv:2608.16443v1 Announce Type: new Abstract: Neurosymbolic (NeSy) Artificial Intelligence aims to integrate Deep Learning (DL) architectures with symbolic reasoning. While initial NeSy approaches have targeted mainly…

Orbit-Planner: Towards Latent World Models for On-Orbit Obstacle Avoidance of Satellite Agents

arXiv:2608.16651v1 Announce Type: cross Abstract: Satellite agents for on-orbit navigation tasks need to predict collision risks using limited onboard observations. However, conventional planners often rely on…

Dynamic Multi-Byte Prediction With Hierarchical Language Models

arXiv:2608.15454v1 Announce Type: new Abstract: Byte-level hierarchical language models (LMs) have recently emerged as a robust alternative to their popular counterparts that use subword tokenization. However,…

ENAF: A Multi-Exit Network with an Adaptive Patch Fusion for Large Image Super Resolution

arXiv:2608.15349v1 Announce Type: cross Abstract: To accelerate single image super-resolution (SISR) networks on large images (2K-8K), many recent approaches decompose an image into small patches and dynamically…

Generated Context versus Governed State: Functional Conditions for Accountable Longitudinal Clinical Reasoning

arXiv:2608.14804v1 Announce Type: new Abstract: Large language models (LLMs) have become the dominant interface of clinical artificial intelligence, yet the interface they expose (text in, text out, one context window…

Pre-training Visual Dexterity in Simulation

arXiv:2608.15917v1 Announce Type: cross Abstract: Large-scale pre-training has made robot policy fine-tuning increasingly data-efficient, but this progress has largely been driven by datasets and embodiments built…

ALKEMIE Agent: an autonomous platform for computational materials design