Topic · Edition
Follow-up to #168097, to ensure extensions can see/use the semantically-correct version. Should have really been done in conjunction with that PR? Useful in cases where a PyTorch extension wants to compare the version…
Make empty MPS addbmm and baddbmm ignore NaN inputs when beta is zero. Reproducer: import torch for device in ("cpu", "mps"): x = torch.full((2, 2), torch.nan, device=device) a = torch.empty(1, 2, 0, device=device) b =…
[torchTLX] tri-state knob with a build-supplied default and a JustKno…
Teach cpp_extension to recognize the win-arm64 VS target and use lib/arm64 for CUDA and cuDNN library paths when building on Windows ARM64. This keeps Windows ARM64 extension builds from looking under x64 CUDA library…
Summary Enable torch._scaled_mm and torch._scaled_mm_v2 OpInfo tests on ROCm FP8-capable GPUs by replacing the blanket TEST_WITH_ROCM skip with PLATFORM_SUPPORTS_FP8. Sample inputs use platform-native FP8 dtypes…
The py3.13/3.14/3.14t clang21 docker images have been failing to build since 2026-08-17. scikit-image==0.22.0 has no cp313/cp314 wheel, so pip builds it from source and resolves an unpinned pythran into the…
[dynamo] Split DequeIteratorVariable off ListIteratorVariable to matc…
[dynamo] Split DequeIteratorVariable off ListIteratorVariable to matc…
[xpu][skip] update skip all platform to skip specific platform for te…
[inductor] AOTI: materialize scalar-in-Tensor-arg for proxy-executor …
Impact: docs only (functorch ensembling tutorial) Risk: low What Removes a duplicated word ("each of of" -> "each of") in a comment in the functorch ensembling tutorial. Why Small typo cleanup in the tutorial source; no…
Includes the following commits: Stop the disabled-IPC-fabric stub from colliding with the real FabricManager (pytorch/kineto#1541) 4f8caaa [ROCm][CI] Restrict PyTorch build to MI350 to reduce CI build time…
[pytorch][PR] Migrate fastAtomicAdd to headeronly (#193176) (#193604)…
LLVM BOLT is a post-link optimizer that optimize's application's code layout based on execution profile gathered by perf. It has been used to optimize NVIDIA's PyTorch containers since 26.04. This PR brings that…
LLVM BOLT is a post-link optimizer that optimize's application's code layout based on execution profile gathered by perf. It has been used to optimize NVIDIA's PyTorch containers since 26.04. This PR brings that…
arXiv:2608.16975v1 Announce Type: cross Abstract: With the rapid advancement of large language models, brain-language decoding has achieved remarkable progress. However, it remains unclear whether decoded content…
arXiv:2608.17293v1 Announce Type: new Abstract: Existing research on irregular time-series forecasting has primarily focused on model design, while evaluation metrics remain insufficiently studied. Existing benchmarks…
arXiv:2608.17556v1 Announce Type: cross Abstract: Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail…
arXiv:2607.19083v3 Announce Type: replace Abstract: Equivariant graph neural networks provide a powerful modeling language for three-dimensional scientific data, but their reuse is often limited by implementations tied…
arXiv:2607.16660v2 Announce Type: replace-cross Abstract: The increasing adoption of Large Language Models (LLMs) as AI components in modern software systems introduces distinct security risks to the software supply…
arXiv:2608.17959v1 Announce Type: cross Abstract: State-of-the-art model-based reinforcement learning methods learn neural world models that allow policy improvement by planning in a latent space, without assumptions on…
arXiv:2608.17366v1 Announce Type: new Abstract: Merging finetuned models combines specialized capabilities without joint training or access to the original data. Most methods operate by linear arithmetic in Euclidean…
arXiv:2607.18046v2 Announce Type: replace Abstract: Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks. However, progress is limited by the lack…
arXiv:2608.17347v1 Announce Type: new Abstract: Repetition is a fundamental mechanism in human learning, where revisiting successful experiences strengthens memory, consolidates skills, and improves future performance.…
arXiv:2605.07304v2 Announce Type: replace Abstract: Bandit algorithms solve diverse sequential decision-making problems, but are often too sample-inefficient for from-scratch personalization. To substantially reduce…
arXiv:2608.17370v1 Announce Type: new Abstract: Generative models promise a route to explainable clinical AI: rather than probe a classifier, model the distributions of healthy and diseased patients and read…
arXiv:2506.14790v3 Announce Type: replace Abstract: Recurring concept drift is pervasive in real-world online time series, where the underlying data-generating process repeatedly alternates between a small set of…
arXiv:2608.17373v1 Announce Type: new Abstract: Sample efficiency is a central challenge in reinforcement learning (RL), particularly in image-based domains where agents must learn from high-dimensional visual inputs.…
arXiv:2511.19513v4 Announce Type: replace Abstract: Decentralized learning often involves a weighted global loss with heterogeneous node weights $\lambda$. We revisit two natural strategies for incorporating these…
arXiv:2606.29519v3 Announce Type: replace Abstract: Long-range learning is hard for recurrent networks trained with stochastic gradient descent, because the influence of a past input fades with the lag $\ell$, and if it…
arXiv:2608.17286v1 Announce Type: new Abstract: Compute-optimal scaling laws guide the training of frontier language models yet remain largely unexplored for visual generation. We present a systematic scaling law study…
arXiv:2608.14635v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents are increasingly trained with reinforcement learning in long-horizon, sandboxed environments. Unlike conventional RL, agentic…
arXiv:2608.16038v2 Announce Type: replace 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…
arXiv:2608.17894v1 Announce Type: cross Abstract: This paper investigates the feasibility of using residual learning to improve unsteady aerodynamic load prediction for aeroelastic applications. The machine learning…
arXiv:2608.16932v1 Announce Type: new Abstract: Multi-layer locate-then-edit methods for knowledge editing first optimize target residual-stream activations (anchors) at selected layers, then realize them layer by layer…
arXiv:2504.20131v4 Announce Type: replace Abstract: We introduce the LZ penalty, a penalty specialized for reducing degenerate repetitions in autoregressive language models without loss of capability. The penalty is…
arXiv:2608.17567v1 Announce Type: new Abstract: Pretrained molecular language models are increasingly used as molecular encoders for learning structure-property relationships. However, their practical suitability for…
arXiv:2608.17713v1 Announce Type: new Abstract: Agent evaluations and trace-based learning often compare outputs across transformed views through a post-response correspondence treated as neutral preprocessing. We show…
arXiv:2608.16955v1 Announce Type: cross Abstract: Post-disaster damage to terrestrial infrastructure can disrupt wireless coverage,while Uncrewed Aerial Vehicle (UAV) swarms provide a promising solution for rapid…
arXiv:2608.17971v1 Announce Type: new Abstract: The impact of climate variability on food production has led to the creation of various forecasting models that uses machine learning (ML), numerical weather predictors…
arXiv:2605.09623v2 Announce Type: replace-cross Abstract: In recent years, the use of artificial intelligence on resource-constrained IoT devices has grown significantly. However, existing approaches to AI task…
arXiv:2608.14308v1 Announce Type: cross Abstract: We study score-matching diffusion models with a convolutional architecture. We argue that the inductive bias of locality means that the machinery of effective field…
arXiv:2608.16974v1 Announce Type: new Abstract: Despite groundbreaking advancements in generative models during the last decade, concerns about their lack of fairness, reinforcing societal inequalities and harming…
arXiv:2408.13323v3 Announce Type: replace-cross Abstract: Solutions of bilevel optimization problems tend to suffer from instability under changes to problem data. In the optimistic setting, we construct a lifted…
arXiv:2605.09058v2 Announce Type: replace-cross Abstract: We introduce Nonlinear GENERIC-Embedded Neural Networks (N-GENNs), a deep learning framework for discovering evolution equations of systems governed by the…
arXiv:2511.17954v2 Announce Type: replace-cross Abstract: Incorporating spatial information, particularly when related to climate, weather, and demographic factors, is crucial for improving underwriting precision and…
arXiv:2311.09614v5 Announce Type: replace-cross Abstract: This study addresses critical gaps in automated lymphoma segmentation from PET/CT images, focusing on issues often overlooked in existing literature. While deep…
arXiv:2608.16939v1 Announce Type: cross Abstract: Training variational quantum models requires choosing between parameter-shift gradients, which are exact but cost $O(P)$ forward evaluations, and simultaneous…
arXiv:2604.15271v4 Announce Type: replace-cross Abstract: Reliable uncertainty estimation is critical for medical image segmentation, where automated contours feed downstream quantification and clinical decision…
arXiv:2608.16928v1 Announce Type: new Abstract: Automatic sensitivity classification of organizational documents is a critical yet underserved problem, where the consequences of misclassification range from regulatory…
arXiv:2608.17620v1 Announce Type: new Abstract: Machine learning models for electroencephalography (EEG) analysis show great promise across a wide range of applications, but their deployment in high-risk domains is…
arXiv:2505.22533v2 Announce Type: replace Abstract: In this paper, we introduce a novel quantum generative model for synthesizing tabular data. Synthetic data is valuable in scenarios where real-world data is scarce or…
arXiv:2608.17981v1 Announce Type: new Abstract: We describe an inference-time architectural enhancement for off-the-shelf foundation models that markedly reduces perplexity and boosts accuracy across generation and…
arXiv:2607.04728v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) post-training for large language models (LLMs) follows a efficient paradigm of "rollout then update", which inevitably results in…
arXiv:2608.17561v1 Announce Type: cross Abstract: The health of marine ecosystems is a critical indicator of global environmental change, yet the physical constraints of underwater observation and the intrinsic…
arXiv:2608.12704v2 Announce Type: replace-cross Abstract: Multi-objective bilevel optimization has wide applications in the AI area such as automated learning and multi-task meta-learning. Although recently some works…
arXiv:2608.17501v1 Announce Type: cross Abstract: Recent efforts toward fully automated AI scientists have demonstrated that language-model agents can generate hypotheses, execute experiments, and draft scientific…
arXiv:2608.17253v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-language models, yet its strongest successes still depend…
arXiv:2608.16923v1 Announce Type: cross Abstract: Networks provide a fundamental representation of relationships among entities. However, real-world networks are often corrupted by noise caused by measurement errors and…
arXiv:2608.17666v1 Announce Type: new Abstract: Bayesian imaging inverse problems often require sampling from high-dimensional posterior distributions. While recent score-based and diffusion models provide expressive…
arXiv:2608.17849v1 Announce Type: new Abstract: Split federated learning (SFL) has emerged as a powerful paradigm for model training at the edge. However, SFL inherently involves discrete decision variables for model…
arXiv:2608.17471v1 Announce Type: cross Abstract: Recent advances in LLM agents have made them increasingly capable of designing methods for complex AI tasks. This raises two central questions about agent-designed…
arXiv:2608.18004v1 Announce Type: new Abstract: Probabilistic modeling of physical fields benefits from both a data-driven prior and known physical structure such as the governing equations. Energy-based models (EBMs)…
arXiv:2603.26747v3 Announce Type: replace-cross Abstract: Recent text-driven motion generation methods span both discrete token-based approaches and continuous-latent formulations. MotionGPT3 exemplifies the latter…
arXiv:2605.31163v3 Announce Type: replace-cross Abstract: We introduce the \emph{design-model framework}: a way to derive efficient recurrent sequence maps from explicit assumptions about memory. A design model writes…
arXiv:2511.06609v5 Announce Type: replace Abstract: The accurate forecasting of complex, high-dimensional dynamical systems from observational data is a fundamental task across numerous scientific and engineering…
arXiv:2608.17802v1 Announce Type: new Abstract: Let $\varepsilon_1,\ldots,\varepsilon_n$ be independent Rademacher signs and let $a=(a_1,\ldots,a_n)\in\R^n$ satisfy the normalization below. For the normalized Rademacher…
arXiv:2608.17948v1 Announce Type: new Abstract: Recent research has leveraged Large Language Models (LLMs) to enhance Automated Feature Engineering (AutoFE) through semantic descriptions and trajectory-based prompting.…
arXiv:2608.17284v1 Announce Type: new Abstract: Irregular time series forecasting is crucial in many domains, such as healthcare and meteorological observation. However, due to the inherent characteristics of irregular…
arXiv:2608.17450v1 Announce Type: cross Abstract: Learning restricted Boltzmann machines (RBMs) is computationally challenging because it requires expectations whose exact evaluation is generally intractable. The…
arXiv:2506.06584v2 Announce Type: replace Abstract: Learning Gaussian Mixture Models (GMMs) is a fundamental problem in statistics and machine learning, with the Expectation-Maximization (EM) algorithm and its popular…
arXiv:2602.21693v2 Announce Type: replace Abstract: Multimodal time series forecasting has garnered significant attention for its potential to provide more accurate predictions than traditional single-modality models by…
arXiv:2602.14784v1 Announce Type: cross Abstract: Breaking long documents into smaller segments is a fundamental challenge in information retrieval. Whether for search engines, question-answering systems, or…
arXiv:2604.20817v2 Announce Type: replace-cross Abstract: Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$. In this paper, we identify a…
arXiv:2608.17956v1 Announce Type: new Abstract: In the Code World Model paradigm an LLM synthesizes an executable world model that a classical planner searches, and the model is accepted when it reproduces sampled…
arXiv:2608.17914v1 Announce Type: new Abstract: Static Timing Analysis (STA) is a critical step in the design flow of digital integrated circuits, however, obtaining accurate delay estimations can represent a challenge…
arXiv:2510.02625v5 Announce Type: replace Abstract: Missing data in tabular datasets forces practitioners into a hard choice: deploy a general-purpose imputer that may perform poorly for the problem at hand, or wait for…
arXiv:2403.15594v4 Announce Type: replace-cross Abstract: Domestic violence is commonly viewed as a gendered issue that primarily affects women, which tends to leave male victims largely overlooked. This study presents…
arXiv:2606.12289v2 Announce Type: replace Abstract: As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their…
arXiv:2205.11930v3 Announce Type: replace-cross Abstract: Human ratings are the gold standard in NLG evaluation. The standard protocol is to collect ratings of generated text, average across annotators, and rank NLG…
arXiv:2608.17542v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs) learn world models by predicting future embeddings, but the objective admits a trivial solution of a constant encoder, so…
arXiv:2608.17423v1 Announce Type: cross Abstract: GRPO is increasingly used for reinforcement learning of vision-language-action (VLA) policies because, unlike PPO, it does not require training a critic. This…
arXiv:2608.17836v1 Announce Type: new Abstract: As large language models (LLMs) are granted increasing autonomy, it is essential to investigate methods that can induce unsafe behavior. We propose a novel white-box…
arXiv:2607.26654v3 Announce Type: replace-cross Abstract: Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whether constitutional midtraining interventions can produce…
arXiv:2510.14656v3 Announce Type: replace-cross Abstract: This work proposes a two-stage physics-informed deep learning framework that combines neural-network-based sampling with statistical inference and constrained…
arXiv:2608.16926v1 Announce Type: new Abstract: Data selection in supervised fine-tuning aims to select a small set of effective samples from large-scale candidate data, reducing training cost while preserving model…
arXiv:2602.12250v2 Announce Type: replace Abstract: Graph neural networks (GNNs) enable powerful unsupervised learning of communities. However, such inference may inadvertently expose sensitive group structures,…
arXiv:2608.17310v1 Announce Type: new Abstract: Reinforcement Learning (RL) has been promising in single-turn LLM fine-tuning. However, long-horizon agentic reasoning introduces increasingly branching interactions and…
arXiv:2605.06866v2 Announce Type: replace Abstract: We study finite-iteration behavior of the exact asynchronous recursions used by categorical distributional temporal-difference methods. The analysis covers scalar…
arXiv:2608.17466v1 Announce Type: cross Abstract: Regularized sparse regression has been extensively studied in the offline setting, but online formulation remains relatively under-explored. This gap stems from four key…
arXiv:2608.17641v1 Announce Type: new Abstract: We present rl-triton, an open-source library of high-performance GPU kernels for reinforcement learning credit assignment, implemented in Triton. The core contribution is…
arXiv:2604.16780v2 Announce Type: replace-cross Abstract: This paper presents FairNVT, a lightweight debiasing framework for pretrained transformer-based encoders that improves prediction fairness while preserving task…
arXiv:2608.16970v1 Announce Type: cross Abstract: LLM-based code generation is now embedded in mission-critical pipelines, but defenses against vulnerable output remain post-hoc -- static analyzers, fine-tuned…
arXiv:2601.22170v2 Announce Type: replace-cross Abstract: Large language models (LLMs) process and predict sequences containing text to answer questions, and address tasks including document summarization, providing…
arXiv:2603.24126v2 Announce Type: replace Abstract: When language models are trained by reinforcement learning (RL) to write probabilistic programs, they can artificially inflate their marginal-likelihood reward by…
arXiv:2606.21828v2 Announce Type: replace-cross Abstract: Neural operators are increasingly used to warm-start Newton solvers for nonlinear PDEs, on the premise that a low test error places the initial guess inside the…
arXiv:2608.17174v1 Announce Type: new Abstract: Chronic kidney disease (CKD) progresses silently and severely undermines quality of life, making early detection critical for improving patient outcomes. We present a…
arXiv:2606.01372v2 Announce Type: replace Abstract: Can neural networks learn algebraic rules from visual inputs, or do they merely fit observed patterns? We study this question using MNIST (or EMNIST letters) as states…
arXiv:2608.16914v1 Announce Type: cross Abstract: Digital learning platforms generate rich behavioural traces (digital markers) that offer the potential to identify struggling students early. This paper investigates…
arXiv:2608.16959v1 Announce Type: cross Abstract: Breast cancer is one of the most common types of cancer among women around the world. Rapid detection and early treatment can hinder its progress to more complex stages…
arXiv:2608.17776v1 Announce Type: new Abstract: We demonstrate that RL finetuning an LLM using debate, a two-player adversarial game between a generator and a critic adjudicated by a weaker LLM judge, reduces reward…
arXiv:2608.17342v1 Announce Type: new Abstract: Forecasting cryptocurrency prices remains a formidable challenge due to inherent non-stationarity, abrupt regime shifts, and multi-scale stochastic dependencies.…
arXiv:2508.05778v2 Announce Type: replace Abstract: Nudging is an empirical data assimilation technique that incorporates an observation-driven control term into the model dynamics. The trajectory of the nudged system…
arXiv:2508.06692v3 Announce Type: replace Abstract: Federated learning systems typically allocate gradient compression by link speed. This is sensible when bandwidth and data informativeness align. However, under…
arXiv:2608.17030v1 Announce Type: cross Abstract: The massive overactuation in the human musculoskeletal system makes it challenging to train musculoskeletal models to generate human-like motion via reinforcement…
arXiv:2608.17646v1 Announce Type: new Abstract: This monograph develops elimination geometry (EG), a typed, native-loss, audit-oriented framework for studying when locally optimal objects can be realized by a shared…
arXiv:2608.12700v2 Announce Type: replace Abstract: Systems that generate GPU kernels with language models report high correctness rates. Those rates come from a single loose test: run the kernel on a few random inputs…
arXiv:2512.22287v4 Announce Type: replace Abstract: Synthetic appliance data are essential for developing non-intrusive load monitoring algorithms and enabling privacy preserving energy research, yet the scarcity of…
arXiv:2608.17093v1 Announce Type: cross Abstract: Existing automotive intrusion detection systems (IDSs) for the Controller Area Network (CAN) largely target discrepancies in message timing, frequency, or sequencing and…
arXiv:2509.06777v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) suffer from oversquashing, where structural bottlenecks limit message propagation between distant nodes, hindering tasks that require…
arXiv:2608.18021v1 Announce Type: new Abstract: WEASEL 2.0 is a dictionary-based time series classifier that combines dilated sliding windows with a randomised hyperparameter ensemble and a fixed-size dense feature…
arXiv:2608.17848v1 Announce Type: new Abstract: Geospatial Foundation Models (GFMs) are emerging as a powerful paradigm for learning semantically rich and geographically consistent visual and physical representations.…
arXiv:2507.03631v5 Announce Type: replace Abstract: Extracting interpretable mathematical models from complex dynamical systems is difficult, especially for chaotic dynamics observed with noisy experimental data. We…
arXiv:2608.17519v1 Announce Type: cross Abstract: Vision-based surgical skill assessment has shown strong in-domain results, yet a fundamental question remains unasked: do these models learn transferable representations…
arXiv:2608.17573v1 Announce Type: cross Abstract: In high-dimensional online prediction, the best predictor may depend on only a few features, so regret should scale with sparsity rather than the ambient dimension.…
arXiv:2605.31156v2 Announce Type: replace Abstract: Causal discovery aims to recover directed causal relations from observational and interventional data, providing a basis for mechanistic understanding and reliable…
arXiv:2604.06416v2 Announce Type: replace-cross Abstract: Although LLM context lengths have grown, there is evidence that their ability to integrate information across long-form texts has not kept pace. We evaluate one…
arXiv:2608.16931v1 Announce Type: new Abstract: Electroencephalography (EEG) foundation models have recently emerged as a promising paradigm for EEG decoding by learning reusable representations from large-scale…
arXiv:2606.31856v2 Announce Type: replace Abstract: We study layered models, including feedforward networks, ResNets, and transformers, by limiting each layer to a width of $d = 3$, i.e., $\mathbb{R}^3$ as…
arXiv:2608.12805v2 Announce Type: replace Abstract: Access to clinical data is essential for developing reliable healthcare machine learning systems, but direct use of electronic health records is constrained by privacy…
arXiv:2608.17440v1 Announce Type: new Abstract: Although Graph Neural Networks (GNNs) have made significant advances in spatio-temporal traffic forecasting, their performance is limited when they rely solely on sensor…
arXiv:2608.17381v1 Announce Type: cross Abstract: Biomolecular design underpins applications from molecular recognition to therapeutics and synthetic biology, yet de novo interaction design remains…
arXiv:2608.16902v1 Announce Type: cross Abstract: The increasing integration of machine learning in healthcare has highlighted critical challenges related to fairness, transparency, and health equity. Specifically, the…
arXiv:2608.18036v1 Announce Type: cross Abstract: MRI reconstruction methods for undersampled k-space data naturally utilize complex-valued measurements. Parallel developments in sparse phase retrieval have shown that…
arXiv:2608.17678v1 Announce Type: new Abstract: Drug discovery and development underpins healthcare but remains costly and failure-prone. A critical bottleneck lies in predicting molecular properties such as solubility,…
arXiv:2608.16978v1 Announce Type: cross Abstract: Turning a frontier vision-language model into a robot policy usually means fine-tuning it to emit an action representation it never saw in pretraining, which throws away…
arXiv:2608.15940v2 Announce Type: replace-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…
arXiv:2608.12447v2 Announce Type: replace Abstract: Trained transformer models develop privileged bases: coordinate axes whose statistics differ from the rest of the residual stream. But what kind of direction does such…
arXiv:2608.17524v1 Announce Type: new Abstract: This preliminary paper outlines a planned evaluation benchmark for Explainable Reinforcement Learning (XRL) methods. Current evaluations rely on functionally-grounded…
arXiv:2608.17180v1 Announce Type: new Abstract: Contextual Reinforcement Learning (CRL) seeks to generalize classical RL by maximizing task coverage across a context space of related tasks. While prior works often train…
arXiv:2608.01658v3 Announce Type: replace-cross Abstract: For mirror descent generated by a Legendre kernel, perhaps one of the most basic question in optimization is this: must every accumulation point of a bounded…
arXiv:2608.16972v1 Announce Type: new Abstract: Machine learning has become an essential component of modern healthcare, where the integration of heterogeneous data sources offers unprecedented opportunities to improve…
arXiv:2401.02020v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs), known for their biologically plausible architecture, face the challenge of limited performance. The self-attention mechanism,…
arXiv:2608.17530v1 Announce Type: cross Abstract: Continual pre-training of large language models must acquire new information without erasing old knowledge. Existing replay methods often choose a global old/new mixture…
arXiv:2608.16930v1 Announce Type: new Abstract: Existing multi-task learning methods rely on hard sharing, multiple paths or experts, adaptive sharing, and dynamic expansion. However, their capacity changes are usually…
arXiv:2608.17753v1 Announce Type: new Abstract: Short-duration heavy-rainfall warning determines whether 1 h rainfall will exceed a threshold within a target-station neighborhood over the next few hours. Multitemporal…
arXiv:2608.17841v1 Announce Type: cross Abstract: Multi-armed bandit algorithms are evaluated by regret, yet comparable regret can coexist with different allocations across independent runs. We study the trade-off…
arXiv:2608.17248v1 Announce Type: cross Abstract: When computational models (either physics-based or data-driven) are used for the sensitivity analysis of engineering systems, the sensitivity estimate is affected by the…
arXiv:2507.15240v2 Announce Type: replace Abstract: For classification with imbalanced class frequencies, i.e., imbalanced classification (IC), standard accuracy is known to be misleading as a performance measure. While…
arXiv:2506.10775v3 Announce Type: replace Abstract: In monotone classification, the input is a multi-set $P$ of points in $\mathbb{R}^d$, each associated with a hidden label from $\{-1, 1\}$. The goal is to identify a…
arXiv:2604.24749v4 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…
arXiv:2608.17592v1 Announce Type: cross Abstract: The communication demands of distributed model prediction control (DMPC) can overwhelm even advanced wireless communication technologies as agents must exchange a…
arXiv:2605.22556v2 Announce Type: replace Abstract: Digital elevation models (DEMs) underpin terrain analysis in Geographic Information Systems (GIS), but commonly as raster representation, they rely on interpolation…
arXiv:2608.17250v1 Announce Type: cross Abstract: This paper develops an adaptive surrogate modeling method for problems with very high-dimensional spatio-temporal outputs. The analysis of spatio-temporal multi-physics…
arXiv:2608.11444v2 Announce Type: replace-cross Abstract: Drug response prediction (DRP) models are an active area of research in pharmacogenomics, with growing potential to accelerate the identification of effective…
arXiv:2603.10302v3 Announce Type: replace Abstract: A plethora of protein language models have been released in recent years. Yet comparatively little work has addressed how to best sample from them to optimize desired…
arXiv:2605.17231v2 Announce Type: replace Abstract: Activation steering has emerged as a lightweight approach for modifying language model behavior without parameter updates, yet existing methods remain brittle:…
arXiv:2608.16971v1 Announce Type: cross Abstract: Radiology reports describe findings and locations in free text, but downstream search and analysis require these relations in a fixed schema. Learning this extraction…
arXiv:2608.02965v3 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…
arXiv:2608.17744v1 Announce Type: cross Abstract: Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource language. On…
arXiv:2608.18066v1 Announce Type: cross Abstract: Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise…
arXiv:2608.16873v2 Announce Type: replace Abstract: High-fidelity finite-element simulations can provide accurate numerical predictions for side-branch resonators, but large simulation datasets are expensive to generate…
arXiv:2608.17947v1 Announce Type: cross Abstract: Large language models can generate executable programs, which makes it possible to search directly over procedural content generators rather than individual levels. We…
arXiv:2605.27219v2 Announce Type: replace Abstract: Collaborative analysis of decentralized confidential datasets is important, but direct sharing of original datasets is often restricted by privacy and institutional…
arXiv:2606.06837v2 Announce Type: replace-cross Abstract: Scripted vs spontaneous speech detection is appealing for interview guardrails, but benchmark performance can be inflated by shortcuts tied to corpus identity,…
arXiv:2608.18026v1 Announce Type: new Abstract: Large-scale, high-dimensional tabular regression remains challenging: tree-based models are robust but lack end-to-end representation learning, while deep models enable…
arXiv:2608.17987v1 Announce Type: cross Abstract: The rapid growth of social media has greatly influenced political discourse, highlighting the need to understand individual political ideologies and their temporal…
arXiv:2608.17687v1 Announce Type: cross Abstract: Despite their widespread use, Large Language Models (LLMs) remain limited by a fundamental problem: the generation of plausible but false content, known as…
arXiv:2608.16373v2 Announce Type: replace 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…
arXiv:2608.16913v1 Announce Type: new Abstract: Road safety monitoring has historically been reactive, relying on crash-record analysis after fatalities and injuries have already occurred. Proactive identification of…
arXiv:2608.17034v1 Announce Type: new Abstract: Post-training can unlock new capabilities and improve performance on specialized tasks, but sometimes at the cost of catastrophic forgetting in other domains. This poses a…
arXiv:2608.17796v1 Announce Type: cross Abstract: Deep learning-based DDoS detectors for 5G-enabled cyber-physical systems face scarce labeled attack data and unrealistic synthetic substitutes, which limit robustness…
arXiv:2608.18040v1 Announce Type: new Abstract: Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has…
arXiv:2605.23037v2 Announce Type: replace Abstract: Two-phase heat transfer underpins boiling, condensation, immersion cooling, flow boiling, energy conversion, and electronics thermal management, but its coupled…
arXiv:2211.14297v5 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…
arXiv:2608.18008v1 Announce Type: new Abstract: Combining large language models with reinforcement learning is increasingly explored, yet the theoretical status of LLM-derived reward signals is often left implicit. We…
arXiv:2608.16925v1 Announce Type: new Abstract: We build an instrument that reads, from a single fit and with no oracle, whether the operator a hybrid PDE-parameter estimator postulates is wrong-and separates that from…
arXiv:2608.17822v1 Announce Type: cross Abstract: Accurate building height information at the individual footprint scale is essential for material stock accounting and post-disaster damage assessments yet remains…
arXiv:2509.25459v4 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…
arXiv:2608.17091v1 Announce Type: new Abstract: While publicly available electricity market data presents a valuable resource for forecasting research, the field lacks established benchmark datasets for standardized…
arXiv:2608.17203v1 Announce Type: cross Abstract: Contrastive learning has become a cornerstone of modern representation learning, powering CLIP-style models that underpin text-to-image generation, vision-language…
arXiv:2608.16921v1 Announce Type: cross Abstract: Effective cybersecurity operations require timely and accurate analysis of large-scale heterogeneous security information; however, analysts increasingly struggle with…
arXiv:2608.17163v1 Announce Type: new Abstract: Off-policy reinforcement learning (RL) has become increasingly sample-efficient, enabling applications such as RL fine-tuning of Vision-Language-Action models into…
arXiv:2608.17775v1 Announce Type: new Abstract: Anomaly detectors are hardest to deploy exactly where training data is scarcest: a newly commissioned production line has a handful of verified "golden" samples and no…
arXiv:2603.04061v2 Announce Type: replace-cross Abstract: Quantum measurements are the means by which we recover messages encoded into quantum states. They are at the forefront of quantum hypothesis testing, wherein the…
arXiv:2607.26369v2 Announce Type: replace Abstract: Rotary Position Embedding (RoPE) has been widely adopted in transformer-based large language models. However, its log-linear frequency schedule, originally designed to…
arXiv:2608.18025v1 Announce Type: new Abstract: GPT-style models achieve strong performance by representing language with finite vocabularies of reusable discrete tokens. This success has motivated symbolic music…
arXiv:2607.09812v2 Announce Type: replace-cross Abstract: Microbial density is clinically important for tumor assessment and treatment decision-making, and recent advances in deep learning suggest that it can be…
arXiv:2509.05574v3 Announce Type: replace-cross Abstract: We prove that, for many standard link invariants, both the proportion of distinct invariant values and the detection probability among prime alternating links…
arXiv:2608.17941v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but relies on costly rollout exploration. Assigning the…
arXiv:2501.05819v2 Announce Type: replace Abstract: Uncrewed Aerial Vehicles (UAVs) are increasingly used in modern communication networks. However, challenges in decision-making and digital modeling continue to hinder…
arXiv:2608.17896v1 Announce Type: new Abstract: Recurrent models process long contexts efficiently by compressing their history into a fixed-size state, but modern architectures typically do so in a single causal pass…
arXiv:2608.17173v1 Announce Type: cross Abstract: Online decision making often requires navigating a landscape shaped by both dynamic contexts and strategic interactions. In competitive pricing, for example, hotels must…
arXiv:2608.17923v1 Announce Type: cross Abstract: Appendicitis is one of the most common abdominal emergencies worldwide and requires prompt diagnosis and treatment to prevent life-threatening conditions. However,…
arXiv:2601.20226v3 Announce Type: replace Abstract: We propose two methodologies for modelling aggregated supply and demand curves in the EPEX SPOT Day-Ahead market, emphasizing generative models as a way to recover…
arXiv:2608.16963v1 Announce Type: new Abstract: Learning analytics often treats unsupervised clusters of intelligent tutoring system (ITS) logs as learner types that should predict learning. We test that assumption on…
arXiv:2608.17411v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has become a widely used approach for post-training Large Language Models (LLMs) for reasoning. In GRPO, the group gradients…
arXiv:2608.17055v1 Announce Type: cross Abstract: Large Language Models (LLMs) are machine learning (ML) models that have an increasingly large carbon footprint through their development and use. Efforts to increase the…
arXiv:2608.17069v1 Announce Type: cross Abstract: Federated deployments of variational quantum classifiers are attractive for cross-organisation risk prediction in supply chains, because raw data never leaves the…
arXiv:2312.06576v2 Announce Type: replace Abstract: Graph Transformers (GTs) facilitate the comprehension of complex relationships on graph-structured data by leveraging self-attention of the possible pairs of nodes.…
arXiv:2608.16929v1 Announce Type: new Abstract: Predicting 30-day hospital readmission is essential for assessing patient stability and optimizing healthcare resources. As clinical risk evolves with the accumulation of…
arXiv:2505.22104v2 Announce Type: replace-cross Abstract: Shielding has emerged as a promising approach for ensuring safety of AI-controlled autonomous systems. The algorithmic goal is to compute a shield, which is a…
arXiv:2608.17957v1 Announce Type: new Abstract: Tabular Foundation Models (TFMs) increasingly rely on in-context learning, where a model receives labelled examples at inference time and predicts labels for new inputs…
arXiv:2608.16927v1 Announce Type: new Abstract: As supervised fine-tuning data continues to scale, selecting high-value subsets from large candidate pools is crucial for reducing training cost and improving model…
arXiv:2608.17333v1 Announce Type: cross Abstract: Modern probabilistic time-series forecasters often express uncertainty through forecast samples. While typically converted into nominal prediction regions using…
arXiv:2603.24472v4 Announce Type: replace-cross Abstract: Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in…
arXiv:2608.17343v1 Announce Type: new Abstract: Data-driven algorithm design frames hyperparameter tuning as a statistical learning problem, but establishing generalization guarantees remains challenging due to the…
arXiv:2608.17616v1 Announce Type: cross Abstract: We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to enable long-context inference without retraining. MoNe reads…
arXiv:2608.17823v1 Announce Type: new Abstract: Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors such as Time Pressure…
arXiv:2608.16947v1 Announce Type: cross Abstract: Huang, Lou, and Xiao introduced Dynamic Mixture-of-Experts Serving and gave an O(sqrt(log k))-competitive randomized algorithm for its integral primal problem, where k…
arXiv:2608.17164v1 Announce Type: new Abstract: Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by external events…
arXiv:2608.17147v1 Announce Type: cross Abstract: Image-to-image face generators are widely used, and visual dissimilarity between their outputs and source images is sometimes treated as evidence of privacy. Auditing…
arXiv:2604.22258v2 Announce Type: replace Abstract: Gaseous microemboli (GME) represent a common complication of cardiac structural interventions across both surgical and transcatheter approaches. Intraoperative…
arXiv:2608.18062v1 Announce Type: cross Abstract: Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities. This can be…
arXiv:2608.17132v1 Announce Type: new Abstract: Recovering the directed acyclic graph (DAG) of a structural equation model (SEM) from observational data is a central problem in causal discovery. The iterative gradient…
arXiv:2608.09218v2 Announce Type: replace Abstract: Score-driven filters update a time-varying parameter by multiplying a scaled log-likelihood score by a scale parameter that controls the magnitude of the update. We…
arXiv:2608.16906v1 Announce Type: cross Abstract: Dynamic community detection is commonly addressed either by full-snapshot recomputation or by solver-specific dynamic procedures. Full recomputation preserves the…
arXiv:2608.17804v1 Announce Type: new Abstract: Practical LLM unlearning is usually evaluated through two objectives: suppress target-specific knowledge and preserve non-target utility. In generative QA, this leaves a…
arXiv:2608.17223v1 Announce Type: cross Abstract: Financial-news direction prediction has become a popular NLP benchmark, yet reported gains depend critically on whether the train-test split is chronological or random,…
arXiv:2608.17246v1 Announce Type: new Abstract: This article investigates several physics-informed and hybrid machine learning strategies that incorporate physics knowledge in experimental data-driven deep-learning…
arXiv:2605.12763v2 Announce Type: replace Abstract: Rich learning in recurrent neural networks often proceeds through sudden transitions in latent dynamics, but there is little theory predicting how gradient descent…
arXiv:2608.17162v1 Announce Type: new Abstract: What a language model internalizes from fine-tuning is usually diagnosed after the fact. We make it an experimental variable. OraclePhys is a systematic fine-tuning…
arXiv:2512.06208v4 Announce Type: replace-cross Abstract: Inference of standard convolutional neural networks (CNNs) on FPGAs often incurs high latency and a long initiation interval due to the deep nested loops…
arXiv:2608.17079v1 Announce Type: new Abstract: Conformal prediction provides distribution-free prediction intervals but relies on exchangeability, an assumption often violated in economic forecasting because of…
arXiv:2608.12710v2 Announce Type: replace Abstract: Muon, a more recently developed optimizer, is useful for matrix-wise models in AI areas. Although many works have studied Muon and its variants, these methods are…
arXiv:2302.12177v5 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…
arXiv:2608.17070v1 Announce Type: new Abstract: With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly important in…
arXiv:2608.16968v1 Announce Type: cross Abstract: In this paper, we consider methods for the diagonal multi-omics integration of heterogeneous datasets. Several approaches to the nature of biological heterogeneity are…
arXiv:2603.08913v2 Announce Type: replace Abstract: Genomic language models (GLMs) have emerged as powerful tools for learning representations of DNA sequences, enabling advances in variant prediction, regulatory…
arXiv:2608.13756v2 Announce Type: replace Abstract: Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable. We test that assumption: holding the checkpoint, prompts,…
arXiv:2608.17181v1 Announce Type: new Abstract: Reinforcement learning (RL) theory fundamentally depends on probability theory through the Markov chain. There is a deep connection between probability theory and…
arXiv:2608.18033v1 Announce Type: cross Abstract: Categorising invoices into the correct General Ledger (GL) code underpins financial reporting and tax compliance. This is a skilled accounting judgement rather than a…
arXiv:2608.17231v1 Announce Type: new Abstract: Low-cost, scalable screening for dementia remains an open problem. Imaging-based diagnosis is costly and hard to deploy widely. Electroencephalography (EEG) is portable…
arXiv:2608.17087v1 Announce Type: new Abstract: Linear temporal logic is a modal extension of propositional logic that allows one to state how a system should behave over time. Its canonical domain is the booleans, but…
arXiv:2608.15062v2 Announce Type: replace-cross Abstract: Scaling transformer language models creates an inherent tension between expressivity and memory efficiency. While unique weights across layers preserve…
arXiv:2509.00203v3 Announce Type: replace Abstract: Parameterized partial differential equations (PDEs) underpin the mathematical modeling of complex systems in diverse domains, including engineering, healthcare, and…
arXiv:2008.08041v3 Announce Type: replace-cross Abstract: In the big data era, deep learning and intelligent data mining technique solutions have been applied by researchers in various areas. Forecast and analysis of…
arXiv:2608.17063v1 Announce Type: new Abstract: Large language models can be fine-tuned into specialized classifiers that perform well across diverse text tasks and make complex judgments, but they typically expose only…
arXiv:2608.17209v1 Announce Type: cross Abstract: End-to-end vision-language-action (VLA) and world-action models offer an elegant route to general-purpose robotics, but their reliability is bounded by validated…
arXiv:2608.18055v1 Announce Type: cross Abstract: Reliable quantitative analysis of dynamic contrast-enhanced MRI requires high-quality spatiotemporal reconstructions at high undersampling rates. Scan-specific…
arXiv:2608.17628v1 Announce Type: cross Abstract: Developing robots capable of understanding and manipulating objects requires compact, interpretable, and generalizable representations. This work proposes a…
arXiv:2606.20560v2 Announce Type: replace Abstract: LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors.…
arXiv:2608.17103v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have achieved remarkable performance in node classification tasks, motivating growing interest in methods capable of explaining their…
arXiv:2606.01846v2 Announce Type: replace Abstract: Mosquito-borne infectious diseases cause more than 700000 deaths worldwide each year. The long-term use of conventional chemical insecticides has induced serious…
arXiv:2608.04180v2 Announce Type: replace Abstract: Feature selection is a critical step in electronic health record (EHR)-based predictive modeling, where input variables are often high-dimensional, sparse, noisy, and…
arXiv:2604.15794v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success, underpinning diverse AI applications. However, they often suffer from performance degradation due to…
arXiv:2608.17151v1 Announce Type: cross Abstract: Cell mimicry arises when different cell types appear morphologically similar. Human pathologists resolve this ambiguity using surrounding tissue context, whereas current…
arXiv:2608.17722v1 Announce Type: cross Abstract: Vision-Language models (VLMs) achieve outstanding performance largely due to the amount of training data available on the internet. At the same time, data holders (e.g.,…
arXiv:2608.17213v1 Announce Type: new Abstract: This paper challenges the pessimistic meta-inductive argument against scientific realism by undermining its inductive step rather than its historical premise. Although…
arXiv:2608.16956v1 Announce Type: cross Abstract: API buyers purchase a dated contract, not a model name alone: the contract includes the requested and served model, reasoning-effort term or its omission, output rail,…
arXiv:2502.00213v5 Announce Type: replace Abstract: Transformers are difficult to optimize with stochastic gradient descent (SGD) and largely rely on adaptive optimizers such as Adam. Despite extensive efforts, the…
arXiv:2608.17135v1 Announce Type: new Abstract: Tensor networks are powerful formats for compressing large-scale data. However, their application to general data processing has been limited by the difficulty of…
arXiv:2604.00547v2 Announce Type: replace-cross Abstract: Unified Multimodal Large Models (UMLMs) integrate understanding and generation capabilities within a single architecture. While unified architectures expand…
arXiv:2608.15790v2 Announce Type: replace Abstract: Crevasse mapping from uncrewed aerial vehicle (UAV) imagery matters for glaciological research and for field safety in glaciated terrain. Yet, pixel-level annotation…
arXiv:2608.16965v1 Announce Type: new Abstract: The dominance of majority classes in real-world datasets poses a fundamental challenge to randomized neural networks, often biasing decision boundaries and overlooking…
arXiv:2608.18061v1 Announce Type: new Abstract: We give a two-player zero-sum repeated game between a learner and nature whose value identity generates Bayesian updating and an exact accounting of exponential-weights…
arXiv:2608.17374v1 Announce Type: cross Abstract: Motivated by a conjecture of Vaikuntanathan and Zamir, we study the pseudo-mixing of Kac's walk on $\mathrm{SO}(n)$: whether short trajectories are indistinguishable…
arXiv:2608.17965v1 Announce Type: new Abstract: Online log anomaly detection is critical for maintaining the reliability of large-scale computing systems. Although recent language model-based log anomaly detectors…
arXiv:2608.17452v1 Announce Type: new Abstract: Machine learning methods predict many real-world systems with remarkable accuracy, but they are typically treated as black boxes that offer no insight into which…
arXiv:2602.06323v3 Announce Type: replace Abstract: Epidemiological forecasting from surveillance data is a hard problem and hybridizing mechanistic compartmental models with neural models is a natural direction. The…
arXiv:2608.17190v1 Announce Type: new Abstract: Dimensionality reduction methods are instrumental to visualize high-dimensional data, and t-SNE stands as one of the most widely used methods due to its emphasis on local…
arXiv:2608.17268v1 Announce Type: new Abstract: Curriculum learning has been widely adopted in the post-training of large language models by organizing training data from easy to hard. However, its effectiveness varies…
arXiv:2608.16905v1 Announce Type: cross Abstract: While the existence of postmortem privacy is increasingly acknowledged (such as the protection of the presence of deceased within digital spaces), far less attention has…
arXiv:2605.31281v2 Announce Type: replace Abstract: As wind turbine fleets age, data-driven reliability engineering and maintenance optimisation are essential to manage lifecycle expenditure and support asset life…
arXiv:2608.18072v1 Announce Type: new Abstract: Purpose: To develop and evaluate a locally deployed multi-agent AI system for radiology report structuring and quality assurance. Materials and Methods: This retrospective…
arXiv:2608.17938v1 Announce Type: new Abstract: Small language models can grade open-ended examination answers as reliably as substantially more expensive models when they grade against an explicit rubric. We test this…
arXiv:2608.17810v1 Announce Type: new Abstract: The evaluation of large language models (LLMs) relies heavily on human-designed assessments, implicitly assuming that AI and humans employ similar underlying cognitive…
arXiv:2510.01832v2 Announce Type: replace Abstract: Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complicates usage, and…
arXiv:2604.03553v3 Announce Type: replace-cross Abstract: AI is increasingly supporting, accelerating, and automating scientific discovery across subjects. Yet, the adoption of AI in historical research remains limited…
arXiv:2604.03237v2 Announce Type: replace-cross Abstract: As AI systems increasingly support human decision making, a central challenge is determining what information helps people recognize when to rely on AI…
arXiv:2608.17330v1 Announce Type: cross Abstract: Large language models for medical consultation are often evaluated after a clinical problem has already been made clear, although real consultations may begin with a…
arXiv:2608.17325v1 Announce Type: new Abstract: Tokenization is a fundamental component of language modeling pipelines. Despite its importance, it is often fixed, even though it significantly impacts model performance…
arXiv:2608.17171v1 Announce Type: new Abstract: Many table-centric NLP tasks such as NL2SQL first retrieve relevant tables from large collections using keyword search. Recent work uses LLMs to generate natural-language…
arXiv:2608.16185v2 Announce Type: replace Abstract: LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections,…
arXiv:2608.17445v1 Announce Type: cross Abstract: Most large language model services use stateless defenses, which judge only the current request, to refuse harmful tasks. Decomposition attacks exploit this limitation…
arXiv:2608.17950v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable multi-hop reasoning capabilities over long contexts, yet the internal mechanisms enabling these distant cognitive leaps…
arXiv:2605.24930v2 Announce Type: replace Abstract: Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and prefill latency…
arXiv:2608.18027v1 Announce Type: new Abstract: Humans continuously learn from experience, whereas conventional large language model (LLM) evaluations ignore the models' ability to improve through inference-time…
arXiv:2601.03570v2 Announce Type: replace Abstract: Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and learning. However,…
arXiv:2608.17075v1 Announce Type: new Abstract: Next-encounter ICD forecasting predicts which standardized diagnosis codes will be documented at a future visit from the longitudinal record available beforehand. The task…
arXiv:2608.17168v1 Announce Type: new Abstract: Reasoning has become a standard technique and feature for contemporary LLMs; however, its application and quality in the context of demanding legal-oriented tasks, such as…
arXiv:2608.17205v1 Announce Type: new Abstract: Vision-language models (VLMs) combine images and text, but when the two conflict and one becomes harder to read, it is unclear how a model shifts its reliance between…
arXiv:2608.17911v1 Announce Type: new Abstract: As LLM agents operate across structured workflows and sessions, preserving long-term history does not ensure that later contexts can recover relevant evidence through a…
arXiv:2608.17827v1 Announce Type: new Abstract: Public institutions face a persistent challenge in selecting LLMs suited to their specific context. Existing benchmarks, however, are of limited use as they primarily…
arXiv:2603.02876v2 Announce Type: replace Abstract: Large Language Model personas, explicit profiles specifying a user's attributes, preferences, and behavioural tendencies, are increasingly used to simulate human…
arXiv:2608.02148v3 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…
arXiv:2604.08525v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are trained to align with user preferences through methods like reinforcement learning. Yet models are beginning to be deployed not…
arXiv:2608.18041v1 Announce Type: new Abstract: Language has two parameters. Count how often words occur together and you estimate amplitude, the strength of association. Word embeddings and attention weights refine…
arXiv:2608.13538v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies…
arXiv:2602.17127v2 Announce Type: replace Abstract: Large language models increasingly serve as reasoning layers in multi-agent systems, where one provider's models may generate, judge, and summarize within a single…
arXiv:2608.17587v1 Announce Type: new Abstract: Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8-11 points worse than using no skill. This gap suggests that…
arXiv:2607.07436v2 Announce Type: replace-cross Abstract: A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures? Skill retirement is the structural…
arXiv:2608.17379v1 Announce Type: new Abstract: We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimization. PTXBench measures…
arXiv:2608.12313v2 Announce Type: replace-cross Abstract: Video creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce cinematic-grade videos. A key…
arXiv:2507.06185v2 Announce Type: replace-cross Abstract: In July 2025, 18 academic manuscripts on arXiv contained hidden instructions that manipulated AI-assisted peer review (indirect prompt injection). Instructions…
arXiv:2503.20182v2 Announce Type: replace Abstract: As large language models (LLMs) increasingly function as human-like assistants exhibiting human-like personality traits, understanding their behavioral characteristics…
arXiv:2608.17188v1 Announce Type: new Abstract: Multi-agent AI workflows are limited not only by model quality but by token cost, latency, and context-window quality. This paper presents a practitioner framework for…
arXiv:2608.17931v1 Announce Type: new Abstract: Recent advances in AI have revolutionized speech processing, yet effective speech understanding requires discerning not just what is said, but how it is said. Speech…
arXiv:2603.30025v3 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…
arXiv:2606.23671v4 Announce Type: replace Abstract: Prior work shows that large language models (LLMs) exhibit introspective capability on benign tasks. We extend the question to safety contexts and examine how reliably…
arXiv:2608.17288v1 Announce Type: new Abstract: GPT attention measures token compatibility through dot-product similarity. This mechanism is simple, effective, and memory-efficient. But it does not explicitly model…
arXiv:2608.17536v1 Announce Type: new Abstract: Legal consultation questions exhibit multi-level complexity. A single retrieval strategy often leads to over-reasoning for simple questions and poor interpretability for…
arXiv:2608.17809v1 Announce Type: new Abstract: Humans naturally form and express beliefs in daily communication, e.g., "I think the answer is 3" or "I suppose that's right." Such beliefs inevitably intertwine with fact…
arXiv:2608.17644v1 Announce Type: cross Abstract: Agents increasingly interpret a person's natural-language preferences by querying an LLM for numerical preference judgments, e.g., by asking how much the person would be…
arXiv:2603.09872v2 Announce Type: replace Abstract: Recent work has found that contemporary language models such as transformers can become so good at next-word prediction that the probabilities they calculate become…
arXiv:2501.06286v3 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…
arXiv:2603.06505v2 Announce Type: replace Abstract: Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings…
arXiv:2608.17150v1 Announce Type: cross Abstract: To effectively collaborate with users on knowledge-intensive tasks, Large Language Models (LLMs) must perform information calibration: matching content to a user's…
arXiv:2608.17053v1 Announce Type: cross Abstract: A bounded agent may obtain information for a decision from its own past, from peers, or from both sources. Retaining task-relevant history can reduce later…
arXiv:2608.12746v2 Announce Type: replace-cross Abstract: Object hallucination in multimodal large language models arises when language priors and corpus co-occurrence bias outweigh the visual evidence, with nothing…
arXiv:2608.17994v1 Announce Type: new Abstract: Using LLMs as judges has become standard practice for evaluating model outputs at scale. This is particularly common for subjective, open-ended tasks such as assessing…
arXiv:2601.07398v2 Announce Type: replace-cross Abstract: Polarization research has demonstrated how people cluster in homogeneous groups with opposing opinions. However, this effect emerges not only through interaction…
arXiv:2608.17102v1 Announce Type: new Abstract: Modern multimodal foundation models (MFMs) have made rapid progress on tasks requiring integrated perception across speech, vision, and language, including emotion…
arXiv:2608.17516v1 Announce Type: new Abstract: Gender bias or other social biases in large language models (LLMs) are frequently evaluated with question answering or survey benchmarks where the LLM needs to give a…
arXiv:2608.16934v1 Announce Type: cross Abstract: RTL code generation is a critical stage in hardware design, and the emergence of agentic systems offers new opportunities to automate this process. To generate correct…
arXiv:2608.17605v1 Announce Type: new Abstract: Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise requests, interrupt…
arXiv:2608.16620v2 Announce Type: replace 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…
arXiv:2608.07531v2 Announce Type: replace Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Existing external rewards…
arXiv:2608.13706v2 Announce Type: replace Abstract: Existing defenses against hallucination in retrieval-augmented and multi-agent pipelines remain partial: evidence is trusted despite modality disagreement, debate…
arXiv:2608.17096v1 Announce Type: new Abstract: The Voynich manuscript (Beinecke MS 408) is usually analysed on three unstated assumptions: that its glyphs are letters, that the strings between blanks are words, and…
arXiv:2602.13110v4 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as scalable judges in pairwise evaluation, but they remain prone to miscalibration and biases. We propose…
arXiv:2608.17356v1 Announce Type: new Abstract: Most automated essay scoring (AES) systems output a single holistic score without interpretable evidence and rely on closed APIs that introduce data privacy and cost…
arXiv:2602.13840v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may…
arXiv:2606.21802v2 Announce Type: replace Abstract: Standard tokenwise diffusion LMs keep training corruption and inference commitment at token granularity throughout denoising. At high noise, this leaves scattered…
arXiv:2608.17719v1 Announce Type: cross Abstract: Context: Software systems that depend on commercial large language model APIs must migrate to successor versions when vendors deprecate older models. Migration decisions…
arXiv:2608.15382v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly proposed for healthcare decision support, but their evaluations still reward single-answer accuracy rather than reasoning…
arXiv:2608.17153v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has significantly enhanced the performance of large language models (LLMs), yet these systems remain vulnerable to knowledge-poisoning…
arXiv:2601.18899v3 Announce Type: replace Abstract: Large Language Model (LLM)-powered Automatic Speech Recognition (ASR) systems achieve strong performance with limited resources by linking a frozen speech encoder to a…
arXiv:2608.17399v1 Announce Type: new Abstract: Text which has been translated from another language tends to carry with it evidence of translation$\unicode{x2014}$hence, it is often referred to as…
arXiv:2608.08032v2 Announce Type: replace-cross Abstract: Safety alignment in multilingual models is uneven: a model that reliably refuses a harmful request in English will often comply with the same request in a…
arXiv:2608.17050v1 Announce Type: new Abstract: Methods for improving knowledge use in large language models typically fall into two regimes. Non-parametric retrieval offers flexible access to external knowledge, but…
arXiv:2607.08642v3 Announce Type: replace Abstract: Speculative decoding accelerates LLM inference by drafting tokens and verifying them in parallel. Block-diffusion drafters such as DFlash model only per-position…
arXiv:2604.02118v2 Announce Type: replace-cross Abstract: Natural language explanations of time series data are increasingly produced by foundation models in high stakes domains, making factual correctness critical.…
arXiv:2608.17866v1 Announce Type: new Abstract: Reconstructing prompts that can elicit a desired answer or behaviour in an LLM is an open and important research topic. Optimisation methods which aim at minimising the…
arXiv:2511.23119v3 Announce Type: replace Abstract: High-quality main content extraction from web pages is a critical prerequisite for constructing large-scale training corpora. While traditional heuristic extractors…
arXiv:2608.17218v1 Announce Type: new Abstract: Works of literature are complicated; they balance plot, suspense, surprise, and artistic expression. Summaries of literature prioritize plot, and therefore may deviate…
arXiv:2608.16894v1 Announce Type: cross Abstract: ML venues shape what kinds of research claims become legible to reviewers and what forms of evidence count as rigorous. The NeurIPS and ICML Position Paper Tracks were…
arXiv:2608.17795v1 Announce Type: new Abstract: Text-to-SQL systems are commonly evaluated using ground-truth SQL queries or reference execution results, but such supervision is unavailable at inference time in…
arXiv:2605.17443v3 Announce Type: replace Abstract: We analyze how automatic speech recognition (ASR) errors propagate through ASR--LLM cascades in Korean spoken question answering (SQA), focusing on downstream semantic…
arXiv:2608.12852v2 Announce Type: replace Abstract: Language can describe states of affairs that are false and states of affairs that could not be the case at all. Whether an AI model internally distinguishes these…
arXiv:2608.16909v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into financial advisory systems, yet their role in reproducing religious bias remains underexamined. This study…
arXiv:2608.12841v2 Announce Type: replace Abstract: We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier experiments to improve…
arXiv:2608.17583v1 Announce Type: new Abstract: Online video platforms can expose young users to harmful content, but independent audits remain difficult because video annotation is costly and moderation judgments vary…
arXiv:2311.06273v1 Announce Type: cross Abstract: The rise of ChatGPT has brought a notable shift to the AI sector, with its exceptional conversational skills and deep grasp of language. Recognizing its value across…
arXiv:2608.17534v1 Announce Type: new Abstract: Large language models increasingly serve as persistent conversational assistants, requiring memory that preserves relevant experience and maintains continuity across…
arXiv:2608.17979v1 Announce Type: new Abstract: Authorship verification (AV) assumes that an author's writing style remains sufficiently stable to distinguish it from that of other writers. In practice, however, this…
arXiv:2502.13428v2 Announce Type: replace Abstract: This work investigates how to improve large language model (LLM)-based reasoning for knowledge base question answering (KBQA) via Monte Carlo Tree Search (MCTS).…
arXiv:2608.17895v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have made significant strides in visual comprehension, their ability to reason about text-dense, professional documents…
arXiv:2605.07725v3 Announce Type: replace Abstract: Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model capacity. While…
arXiv:2608.17120v1 Announce Type: new Abstract: Children learn hundreds of words over the first years of their lives, in a process that begins slowly but quickly picks up speed. Prior models describe vocabulary growth…
arXiv:2608.17843v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong performance on structured reasoning tasks, but what they encode and whether it informs model behavior remain unclear.…
arXiv:2603.23047v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) fine-tuning has shown substantial improvements over vanilla RAG, yet most studies target document question answering, leaving open…
arXiv:2608.18011v1 Announce Type: new Abstract: Reasoning in LLMs is overwhelmingly studied in domains that provide a model with rules: mathematics and code. Linguistic puzzles invert this: the solver must first…
arXiv:2607.27155v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for…
arXiv:2608.17051v1 Announce Type: new Abstract: Secondary use of electronic health records requires de-identification, yet existing systems miss \emph{institutionally situated} protected health information (PHI) such as…
arXiv:2608.17454v1 Announce Type: new Abstract: This paper presents a pipeline for analyzing media bias and framing in online news. The pipeline groups articles into topics and events, adds named-entity and sentiment…
arXiv:2402.09696v3 Announce Type: replace Abstract: Current Grammar Error Correction (GEC) initiatives tend to focus on major languages, with less attention given to low-resource languages like Esperanto. In this…
arXiv:2608.04772v2 Announce Type: replace Abstract: Scaling supervision for multi-turn medical agents is difficult because expert dialogue annotation is costly and clinical conversations are privacy-restricted. We…
arXiv:2608.17550v1 Announce Type: cross Abstract: Academic papers are a primary carrier of scientific knowledge, yet most of this knowledge remains locked in PDFs that are optimized for human reading rather than machine…
arXiv:1908.06361v2 Announce Type: replace Abstract: Word embeddings are often criticized for capturing undesirable word associations such as gender stereotypes. However, methods for measuring and removing such biases…
arXiv:2503.00992v3 Announce Type: replace-cross Abstract: Background. Evidence that large language models (LLMs) reproduce human judgments does not establish conceptual mastery: the correspondence may reflect…
arXiv:2607.15209v2 Announce Type: replace Abstract: Multilingual pre-trained language models such as XLM-R perform well for major languages but struggle with low-resource Ge'ez-script languages, largely due to high…
arXiv:2604.06474v2 Announce Type: replace Abstract: Deep research with Large Language Model (LLM) agents is emerging as a powerful paradigm for multi-step information discovery, synthesis, and analysis. However,…
arXiv:2608.17084v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) increasingly answer questions whose correctness depends on visual, textual, temporal, acoustic, document, chart, or embodied…
arXiv:2608.17184v1 Announce Type: new Abstract: Job Safety Analysis (JSA) and pre-task planning can benefit from prior incident records, yet historical accident data is often stored as unstructured narratives that are…
arXiv:2608.17088v1 Announce Type: new Abstract: A central goal of multilingual NLP is to achieve high monolingual performance per language and cross-lingual alignment for large-scale language coverage with a…
arXiv:2608.17781v1 Announce Type: new Abstract: ML systems increasingly condition decisions on downstream model identity, but this is useful only if model-specific differences form reusable structure rather than…
arXiv:2601.18747v3 Announce Type: replace-cross Abstract: Modern AI agents increasingly rely on search infrastructure to execute complex, neuro-symbolic reasoning workflows. These workflows often compile into deeply…
arXiv:2605.07507v2 Announce Type: replace Abstract: The rapid growth of academic publications has created a need for tools that extract structured knowledge from unstructured scientific texts. Although large language…
arXiv:2608.09106v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong performance across a wide range of legal tasks. In legal practice, time is a critical concept that governs the…
arXiv:2608.17596v1 Announce Type: cross Abstract: In this study, we investigate developmental mechanisms that enable small, resource-constrained systems such as cm-sized millirobots to autonomously explore, learn, and…
arXiv:2503.14229v5 Announce Type: replace Abstract: Vision-and-Language Navigation (VLN) has been studied mainly in either discrete or continuous spaces, with little attention to dynamic, crowded environments. We…
arXiv:2608.13333v3 Announce Type: replace Abstract: Large neighborhood search normally selects a random subset of decision variables for iterative optimization. To efficiently solve various problems, researchers tend to…
arXiv:2608.17638v1 Announce Type: new Abstract: What a reasoning model writes is only a partial record of the process that produces it. We introduce a two-level internal readout for mixture-of-experts reasoning. We…
arXiv:2608.17933v1 Announce Type: new Abstract: Financial time series exhibit non-stationary and heterogeneous statistical properties, making change-point detection challenging because no single unsupervised algorithm…
arXiv:2608.17829v1 Announce Type: cross Abstract: LLMs increasingly rely on external contexts, such as pre-defined system prompts or retrieved documents, to improve generation quality. However, processing these contexts…
arXiv:2608.17597v1 Announce Type: cross Abstract: Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions. Existing…
arXiv:2608.18056v1 Announce Type: new Abstract: Urban traffic congestion reduces productivity and increases travel cost and emissions. Network-wide live travel-time shortest-path rerouting can be highly effective in…
arXiv:2608.17588v1 Announce Type: new Abstract: Agent Skills package reusable natural language procedures with executable resources, enabling software agents to acquire task specific capabilities without model…
arXiv:2608.04457v2 Announce Type: replace-cross Abstract: As "AI Scientists" emerge to drive research via the Model Context Protocol (MCP), systems relying on ephemeral scripts will fail. The sheer scale of stateful,…
arXiv:2608.17167v1 Announce Type: cross Abstract: Active inference selects actions by minimising an expected free energy functional over predicted futures. However, adding an expectation over yet-unobserved outcomes…
arXiv:2608.17007v1 Announce Type: new Abstract: Agent Skills can specify procedural and resource obligations for tool use, and language models instantiate them as concrete programs. However, when models turn this…
arXiv:2608.17659v1 Announce Type: cross Abstract: LLM-powered GUI agents that autonomously operate smartphones are rapidly transitioning from research prototypes to early real-world deployment. However, because these…
arXiv:2406.08534v4 Announce Type: replace-cross Abstract: This paper addresses the NP-hard problem of optimizing container handling at ports by integrating Quay Crane Dual-Cycling (QCDC) and dockyard rehandle…
arXiv:2512.06040v2 Announce Type: replace-cross Abstract: Voice authentication systems deployed at the network edge face dual threats: a) sophisticated deepfake synthesis attacks and b) control-plane poisoning in…
arXiv:2608.17071v1 Announce Type: new Abstract: We present KernelArc, a multi-agent framework for autonomous GPU kernel optimization across heterogeneous workloads. Strategy-specialized agents run in parallel and…
arXiv:2606.08093v2 Announce Type: replace Abstract: Pathology is the cornerstone of modern medicine, where accurate decision-making relies heavily on evidence-based practices. While artificial intelligence (AI) has the…
arXiv:2608.17499v1 Announce Type: new Abstract: User-facing tool agents must coordinate dialogue and tool use as user goals unfold over multiple turns. Yet interactive reinforcement learning typically reduces each…
arXiv:2608.17301v1 Announce Type: new Abstract: Post-training with supervised chain-of-thought fine-tuning and reinforcement learning from verifiable rewards has substantially improved the mathematical reasoning…
arXiv:2608.16918v1 Announce Type: cross Abstract: Patent prior-art retrieval is a recall-oriented search task over long and highly structured technical documents. Dense retrieval improves semantic matching, but…
arXiv:2608.17684v1 Announce Type: new Abstract: Self-evolving agents turn experience into reusable skills, workflows, or memories, but post-evolution accuracy alone does not show whether learned behavior preserves…
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…
arXiv:2608.10442v2 Announce Type: replace-cross Abstract: Automatic stress detection from facial video offers a practical path to non-intrusive affect monitoring, yet existing video-based approaches commonly decompose…
arXiv:2608.17928v1 Announce Type: cross Abstract: In the Lifelong Multi-Agent Path Finding (L-MAPF) problem, agents must repeatedly move from one destination to another while avoiding obstacles and inter-agent…
arXiv:2608.14603v2 Announce Type: replace-cross Abstract: Cooperative perception enables vehicles and infrastructure to exchange sensor data via Vehicle-to-Everything (V2X) communication, extending sensing coverage…
arXiv:2608.17760v1 Announce Type: cross Abstract: Intelligent channel state information (CSI) feedback is essential for realizing the high capacity and spectral efficiency goals of future 6G systems, yet existing deep…
arXiv:2608.17564v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) are motivated by the hope that understanding and generation reinforce each other but controlled ablations repeatedly find that adding a…
arXiv:2605.16024v2 Announce Type: replace Abstract: Desktop GUI agents operate under partial observability: visually similar screens can correspond to different underlying workflow states, so locally plausible actions…
arXiv:2608.17571v1 Announce Type: cross Abstract: Motivation: Low-dimensional embeddings are widely used to explore cell-state heterogeneity in single-cell and other high-dimensional biological data. Although many…
arXiv:2608.03744v2 Announce Type: replace Abstract: Clinical decision support is moving toward committees of language-model agents deliberating on a shared workspace. We ask whether such committees can be gamed by…
arXiv:2608.17906v1 Announce Type: new Abstract: Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains…
arXiv:2608.17574v1 Announce Type: new Abstract: How cautious should an agent be while it is still learning its environment? We propose RATTL (Risk-Adversarial Total-Reward Learning), which ties caution to epistemic…
arXiv:2608.17671v1 Announce Type: cross Abstract: Automated security patch backporting is critical for mitigating N-day vulnerabilities. Recent tools report success rates above 80% on their respective datasets. However,…
arXiv:2608.17176v1 Announce Type: cross Abstract: An AI audit record is useful only if its durability and trust boundary are explicit. Returning a guarded decision before any durable write minimizes latency, but it…
arXiv:2608.17067v1 Announce Type: new Abstract: As text-to-image generative models advance, they raise critical safety concerns, particularly the generation of Not-Safe-For-Work (NSFW) content such as violence and…
arXiv:2607.01854v2 Announce Type: replace-cross Abstract: Can a platform tell, before deployment, whether an open-weight checkpoint has had its refusal mechanism stripped? Runtime guards cannot: they score generations,…
arXiv:2409.14644v4 Announce Type: replace-cross Abstract: The advent of large language models (LLMs) has significantly advanced artificial intelligence in software engineering, with source code embeddings playing a…
arXiv:2509.10818v2 Announce Type: replace Abstract: When consequential decisions depend on knowledge that exists nowhere in writing, LLMs hallucinate not from retrieval failure but from model absence. RAG and…
arXiv:2608.17360v1 Announce Type: cross Abstract: Reliable jailbreak evaluation is essential for assessing LLM safety, but most existing studies rely solely on attack success rate (ASR) without accounting for its…
arXiv:2608.17220v1 Announce Type: cross Abstract: Autonomous AI agents are emerging as interfaces for decentralized finance (DeFi) actions such as swaps, lending operations, and yield management. Because these agents…
arXiv:2608.01324v2 Announce Type: replace Abstract: Deep search has become a fundamental capability of large language models (LLMs) for solving open-domain complex tasks. However, existing approaches typically rely on…
arXiv:2608.18058v1 Announce Type: new Abstract: Autonomous LLM agents that converse on a user's behalf are an emerging design pattern in matching platforms, yet their viability depends on a condition rarely examined:…
arXiv:2604.09508v3 Announce Type: replace-cross Abstract: Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents. To tackle complex queries…
arXiv:2608.17183v1 Announce Type: new Abstract: Small Language Models (SLMs) are increasingly deployed in resource-constrained, privacy-sensitive settings, where safety and bias failures can cause security and societal…
arXiv:2608.17917v1 Announce Type: cross Abstract: Automatic Target Detection and Recognition (ATD/R) is critical for military decision support and (semi-)autonomous operations. Recent advances in object detection and…
arXiv:2608.17306v1 Announce Type: cross Abstract: While adversarial prompt tuning can enhance robustness of vision-language models efficiently, we find that existing methods aggravate robust generalization overfitting…
arXiv:2608.15565v2 Announce Type: replace Abstract: Experience-learning agents for optimization modeling improve by storing verified skills, but existing learners admit knowledge by checking against known answers, which…
arXiv:2608.16177v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as agents that operate equipment, execute instructions, and act inside institutional hierarchies, raising…
arXiv:2608.17715v1 Announce Type: cross Abstract: Credit decisioning is a high-stakes task in which model outputs must be accurate and explainable to support compliant decisions. Although modern credit risk models such…
arXiv:2608.07994v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) is essential for enterprise knowledge question answering (QA), particularly in domains with complex product documentation like…
arXiv:2607.16207v2 Announce Type: replace Abstract: Public open-weight language models are often fine-tuned on private or domain-specific data before deployment, creating a need to audit whether individual records were…
arXiv:2608.17237v1 Announce Type: cross Abstract: Converting structural framing plans into editable finite-element model drafts remains labor-intensive and prone to transcription error. Existing drawing-understanding…
arXiv:2605.27563v2 Announce Type: replace-cross Abstract: We prove an elementary bounded-differences inequality for functions of non-isotropic Gaussian vectors. Specifically, if $f$ has bounded coordinate differences…
arXiv:2608.18076v1 Announce Type: cross Abstract: Large-scale image generation has benefited from advances in data scale, quality, rebalancing, and recaptioning, yet conventional pipelines typically optimize…
arXiv:2608.17299v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) have recently emerged as a highly promising paradigm for cross-domain zero-shot forecasting. However, existing evaluation protocols…
arXiv:2608.17304v1 Announce Type: cross Abstract: Formal verification is a crucial technique for ensuring the functional correctness of hardware designs. In the context of property checking, a key challenge is how to…
arXiv:2608.18050v1 Announce Type: new Abstract: AI agents increasingly perform knowledge work (i.e., produce and modify persistent digital artifacts such as code repositories, documents, spreadsheets, slides, reports),…
arXiv:2608.17634v1 Announce Type: new Abstract: The $\operatorname{do}$-operator is described graphically by deleting arrows into its targets and functionally by replacing their mechanisms with constants. To call these…
arXiv:2608.16896v1 Announce Type: cross Abstract: This paper presents the design and outcomes of a seven-weekend AI storytelling program developed for Black girls aged 10-12. Grounded in Afrofuturism and Black feminist…
arXiv:2608.17128v1 Announce Type: new Abstract: A personal AI system needs a model of the user's goals, constraints, and ongoing commitments to plan and act on their behalf, and the quality of that model is bounded by…
arXiv:2604.26703v2 Announce Type: replace-cross Abstract: Scientific discovery often begins where observation and prediction disagree. As computation and machine learning survey chemical space, experiment-simulation…
arXiv:2606.14438v4 Announce Type: replace-cross Abstract: End-to-end (E2E) autonomous-driving planners trained by imitation are prone to statistical shortcuts: they associate scene elements that merely co-occur with…
arXiv:2608.17834v1 Announce Type: cross Abstract: Large language models are pushing data science toward increasingly autonomous and agentic workflows, with recent systems already supporting multi-step and long-running…
arXiv:2608.18017v1 Announce Type: new Abstract: Improving flight safety with flight data requires not only accurate detection of risk events, but more importantly, clear interpretation of their underlying causes at the…
arXiv:2608.17341v1 Announce Type: new Abstract: AI planning is concerned with finding a sequence of actions that achieves a specified goal. It relies on explicit models of the world, commonly represented in the Planning…
arXiv:2608.17433v1 Announce Type: new Abstract: LLM agents have been widely adopted to operate mission-critical infrastructure (MCI). These agents normally rely on a harness that determines what information they can…
arXiv:2608.17344v1 Announce Type: cross Abstract: Neural network surrogates are an emerging alternative to traditional electromagnetic wave simulators like finite-difference time-domain (FDTD); their goal is to replace…
arXiv:2507.15455v3 Announce Type: replace-cross Abstract: We propose a mesh-free policy iteration framework that combines classical dynamic programming with physics-informed neural networks (PINNs) to solve…
arXiv:2606.01008v2 Announce Type: replace-cross Abstract: We present a benchmark for evaluating AI models and agents on real-world formal software verification tasks. We first scrape 11,039 property-based tests (PBTs)…
arXiv:2608.07565v2 Announce Type: replace-cross Abstract: Conversational assistants increasingly recommend follow-up edits to help users continue a task. Existing systems primarily target text-only interactions, leaving…
arXiv:2608.16897v1 Announce Type: cross Abstract: Large-scale urban simulation plays a pivotal role in social science, traffic safety, and transportation policy. Recent work has shown that large language models, when…
arXiv:2608.17522v1 Announce Type: cross Abstract: Persistent shortages in the surgical workforce and inherent limitations of traditional training methods highlight the necessity of automated, data-driven approaches in…
arXiv:2608.17255v1 Announce Type: cross Abstract: X-ray imaging can be approximately modeled as the projection of an underlying volumetric attenuation field, with each measurement recording the accumulated attenuation…
arXiv:2608.17244v1 Announce Type: cross Abstract: This paper addresses the limitations of Gaussian distribution assumptions in statistical sparse learning, particularly in modeling correlated and heterogeneous data.…
arXiv:2406.01586v4 Announce Type: replace-cross Abstract: Diffusion models have been verified to be effective in generating complex distributions from natural images to motion trajectories. Recent diffusion-based…
arXiv:2608.17756v1 Announce Type: new Abstract: Memory is a key capability of LLM agents. Persistent memory extends this across sessions---enabling recall, revision, and personalization. Yet its multi-stage pipeline…
arXiv:2608.16900v1 Announce Type: cross Abstract: Language-model agents increasingly produce quantum-science results; we ask whether the same agentic paradigm can also scrutinize them in an auditable, reproducible, and…
arXiv:2506.18682v3 Announce Type: replace-cross Abstract: Recent advances in autonomous driving (AD) have highlighted the potential of hyperspectral imaging (HSI) for enhanced environmental perception, particularly in…
arXiv:2607.12982v3 Announce Type: replace Abstract: Math reasoning has achieved significant progress with the rapid advancement of Multimodal Large Language Models (MLLMs), however analytic geometry remains largely…
arXiv:2608.17731v1 Announce Type: new Abstract: Diversity is a fundamental criterion for evaluating generative artificial intelligence (AI) systems, yet its measurement remains inherently ambiguous. Existing approaches…
arXiv:2606.07464v2 Announce Type: replace-cross Abstract: Monolithic vision-action models represent an emerging paradigm in autonomous driving. However, this architecture produces token sequences that quickly exceed…
arXiv:2608.16907v1 Announce Type: cross Abstract: Generative AI (GenAI) is rapidly reshaping education by unlocking the potential for personalized tutoring. Yet, emerging platforms largely focus on GenAI chatbot tutors…
arXiv:2608.17694v1 Announce Type: cross Abstract: Existing LLM-based approaches to Architecture Decision Record (ADR) generation share a critical and largely unexamined assumption: that input is already reasonably…
arXiv:2608.16910v1 Announce Type: cross Abstract: National AI strategies increasingly guide governance, workforce development, innovation, and competitiveness, but less is known about how they frame education as a…
arXiv:2608.16984v1 Announce Type: cross Abstract: Recent monocular depth estimators achieve strong zero-shot generalization, yet often struggle to preserve fine-grained structures and object boundaries. We attribute…
arXiv:2608.17718v1 Announce Type: new Abstract: Long-horizon agents increasingly operate across many steps, tools, and observa- tions. In this setting, the relevant oversight question is not only whether each action is…
arXiv:2608.17195v1 Announce Type: cross Abstract: We present Graphectory Viewer, a web-based tool for interactive, process-centric analysis of software-agent trajectories. Building on the Graphectory representation…
arXiv:2608.17741v1 Announce Type: new Abstract: OWL 2 DL ontologies, grounded in the description logic $\mathcal{SROIQ}$, express large knowledge bases in biomedicine and the Semantic Web. Neuro-symbolic (NeSy) learners…
arXiv:2506.01297v5 Announce Type: replace Abstract: Representation learning of geospatial locations remains a core challenge in achieving general geospatial intelligence, with increasingly diverging philosophies and…
arXiv:2608.17932v1 Announce Type: cross Abstract: Groups routinely complete projects that no single member can plan, execute, or verify alone. We propose a formal model of this phenomenon, Collective Counterfactual…
arXiv:2608.14825v2 Announce Type: replace-cross Abstract: Frontier LLM agents increasingly transact on behalf of separate principals, often using natural language rather than structured APIs. Much of the safety…
arXiv:2608.17856v1 Announce Type: new Abstract: Tabular prediction is a critical task across numerous applications. The recent success of large language models has sparked various approaches for adapting them to the…
arXiv:2608.17799v1 Announce Type: cross Abstract: Ground-to-Air (G2A) drone detection in medium- and long-wave infrared (MWIR/LWIR) imagery is challenging due to reduced texture information, sensor noise, weak thermal…
arXiv:2608.17092v1 Announce Type: cross Abstract: Autonomous vehicles (AVs) depend on reliable Global Navigation Satellite System (GNSS) positioning. However, spoofed GNSS signals can induce plausible but incorrect…
arXiv:2608.17148v1 Announce Type: cross Abstract: A personal language agent learns a fact from one audience and may later place it in the prompt it assembles for another. This memory-to-context step is an attack…
arXiv:2608.17336v1 Announce Type: new Abstract: Long-context prefill in large language models (LLMs) incurs substantial computation and memory traffic because dense self-attention computes quadratic query-key scores.…
arXiv:2608.17468v1 Announce Type: new Abstract: Storyboards turn screenplays into visual shot plans for automated short drama production. Professional storyboarding relies on tacit directorial expertise and remains an…
arXiv:2608.17234v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used to interact with screenshots, scanned documents, diagrams, and other visually grounded inputs. This shift…
arXiv:2608.17434v1 Announce Type: new Abstract: We study Gaussian regression over the explicit vector-valued Parhi--Nowak deep-RBV^2 architecture with depth L, width w, layer-sum variation budget A, and output bound B.…
arXiv:2608.17352v1 Announce Type: new Abstract: Distributed Denial-of-Service (DDoS) attacks threaten network availability, requiring a cognitive detection process that senses traffic, infers intent, and supports an…
arXiv:2508.08748v2 Announce Type: replace-cross Abstract: Robotic pick-and-place tasks in convenience stores pose challenges due to dense object arrangements, occlusions, and variations in object properties such as…
arXiv:2608.17983v1 Announce Type: cross Abstract: Ultrasound tongue contour segmentation remains challenging under cross-dataset domain shift, where limited annotations, probe variability, and acquisition noise often…
arXiv:2608.17271v1 Announce Type: new Abstract: Artificial superintelligence (ASI) requires AI to move beyond mastering existing knowledge toward exploring the unknown, creating new knowledge, and turning new ideas into…
arXiv:2608.17289v1 Announce Type: new Abstract: Group-relative policy optimization has emerged as a key paradigm for training agentic large language models (LLMs) on multi-turn interactive tasks. However, most existing…
arXiv:2608.11210v2 Announce Type: replace Abstract: Bayesian calibration of process-based models requires a prior distribution for each model parameter. Despite decades of methodological work, researchers almost always…
arXiv:2411.15455v3 Announce Type: replace-cross Abstract: Accurately predicting the popularity of micro-videos is a critical but challenging task, characterized by volatile, `rollercoaster-like' engagement dynamics.…
arXiv:2605.09948v2 Announce Type: replace Abstract: Current Vision-Language-Action (VLA) models typically treat the deepest representation of a vision-language backbone as universally optimal for action prediction.…
arXiv:2608.17618v1 Announce Type: cross Abstract: Learning analytics models can identify students at risk of poor performance, but they do not directly indicate which interventions are feasible, actionable, and…
arXiv:2608.17749v1 Announce Type: new Abstract: Decentralised partially observable Markov decision processes (DecPOMDPs) provide a general framework for modelling multi-agent decision making under uncertainty. However,…
arXiv:2608.17323v1 Announce Type: cross Abstract: Robotic manipulation policies trained via imitation learning, such as Action Chunking with Transformers (ACT), can achieve strong performance under ideal conditions but…
arXiv:2605.29976v3 Announce Type: replace-cross Abstract: We evaluate the climate simulation capabilities of ArchesWeather and ArchesWeatherGen, two machine learning models originally trained for weather forecasting and…
arXiv:2608.17919v1 Announce Type: cross Abstract: Background and Context: Question and inquiry are integral parts of knowledge seeking and learning. Despite their importance, students tend not to ask enough questions in…
arXiv:2606.31222v2 Announce Type: replace Abstract: Composed image retrieval requires identifying a target image from a gallery by integrating a reference image with a textual modification instruction. In a…
arXiv:2608.17515v1 Announce Type: cross Abstract: Background: Large Language Models (LLMs) are increasingly being applied to Software Engineering (SE) tasks, achieving high accuracy across problems such as clone…
arXiv:2608.17282v1 Announce Type: new Abstract: Existing agentic reasoning systems typically rely on centralized protocols. This design introduces routing bottlenecks and static role allocations that often fail when…
arXiv:2606.03895v3 Announce Type: replace-cross Abstract: Large language model (LLM) agents can persist across tasks, acquire memory, activate Skills, synthesize tools, fork child processes, attach remote resources, and…
arXiv:2607.09520v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are the perceptual backbone of embodied AI, but their energy footprint on edge hardware remains poorly understood. Existing…
arXiv:2608.15546v2 Announce Type: replace Abstract: Most LLM-based automated algorithm design methods optimize a designated component within a human-specified scaffold, fixing overall organization and component…
arXiv:2605.14889v4 Announce Type: replace-cross Abstract: Online surgical phase recognition must commit to a prediction at every frame of a procedure that runs for hours, from past frames alone and at a per-frame cost…
arXiv:2608.14947v2 Announce Type: replace Abstract: Detecting opioid craving from wearable physiological signals is critical yet difficult, with the potential to support proactive interventions for individuals with…
arXiv:2608.17124v1 Announce Type: new Abstract: Combining the answers a large language model (LLM) samples for a question into one decision is a test-time information fusion problem, usually solved by majority voting.…
arXiv:2608.17929v1 Announce Type: new Abstract: Robust Markov decision processes optimize one policy against a set of plausible transition functions. This can be conservative when the unknown dynamics are fixed and…
arXiv:2608.16903v1 Announce Type: cross Abstract: The deployment of machine learning systems capable of detecting covert consciousness in neurologically injured patients creates a profound challenge at the intersection…
arXiv:2608.16916v1 Announce Type: cross Abstract: Calculating average distances in large-scale networks is computationally intensive and constrained by limited main memory, posing a significant challenge in graph…
arXiv:2608.17443v1 Announce Type: new Abstract: Knowledge Graph Reasoning (KGR) aims to discover latent facts by leveraging the structural evidence available in KGs, posing a challenge to the structural semantic…
arXiv:2608.17426v1 Announce Type: cross Abstract: We introduce Semantic Task Completion Video Generation, an outcome-oriented video generation task. Under this formulation, success requires both achievement of the…
arXiv:2608.11733v2 Announce Type: replace-cross Abstract: In this work, we presented, to the best of our knowledge, the first reported 12-CNOT decomposition of the double qubit excitation operator. We compared our new…
arXiv:2608.01035v4 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely…
arXiv:2608.17247v1 Announce Type: new Abstract: Personalized agents must decide whether retrieved user memory should be used, ignored, updated, or queried before it affects a current task. We use this setting to develop…
arXiv:2608.13584v2 Announce Type: replace-cross Abstract: UltraArUco is a lightweight multilingual library and framework for low latency, realtime marker-based tracking in mobile augmented reality. Unlike standard…
arXiv:2608.16924v1 Announce Type: cross Abstract: This work-in-progress (WIP) innovative practice category paper presents LLM Odyssey, an open source, browser-based serious gaming platform comprising 13 interactive…
arXiv:2608.17997v1 Announce Type: cross Abstract: Artificial intelligence (AI) is becoming part of the working infrastructure of the biosciences. AI models can predict biomolecular structures, design proteins, rank…
arXiv:2608.17528v1 Announce Type: new Abstract: Modern agents operate inside agent harnesses that manage tools, context, and control flow, making the harness a critical part of the agent system. Our original Agent…
arXiv:2608.16891v1 Announce Type: new Abstract: Agentic AI systems request tool actions that can modify files, send messages, launch jobs, or change workflow state. This shifts the safety problem from harmful text…
arXiv:2608.16890v1 Announce Type: new Abstract: Clinical trial programming -- transforming study protocols into analysis-ready datasets under CDISC standards -- is a bottleneck in regulatory submissions, yet LLM-based…
arXiv:2608.16919v1 Announce Type: cross Abstract: Recent advances in large language models and agent-based recommendation frameworks have introduced new opportunities for more flexible and context-aware recommendation.…
arXiv:2602.20134v2 Announce Type: replace-cross Abstract: Epidemiological models increasingly rely on crowdsourced, self-reported behavioral data such as vaccination status, mask usage, and social distancing adherence.…
arXiv:2608.16893v1 Announce Type: cross Abstract: Expert surveys are widely used in security research to study practitioner workows and decision-making, yet recruiting domain experts - especially in Security Operations…
arXiv:2608.17632v1 Announce Type: cross Abstract: Large language models (LLMs) can both expand underspecified queries and encode text as dense representations, suggesting a unified model for query expansion and…
arXiv:2608.12898v2 Announce Type: replace-cross Abstract: Document parsing aims to transform unstructured documents into structured and machine-readable representations. Recent advances in Vision-Language Models (VLMs)…
arXiv:2608.17625v1 Announce Type: new Abstract: Saudi Arabia will host the 2034 FIFA World Cup and already operates crowd management at Hajj scale. Drone-based counting must hold accuracy on footage unlike anything in…
arXiv:2608.17044v1 Announce Type: cross Abstract: The 10th AI City Challenge, held with ECCV 2026, marks a decade of community benchmarking for intelligent transportation, smart cities, and physical AI. Since its 2017…
arXiv:2606.07897v2 Announce Type: replace Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user. Existing evaluations typically measure this either by assessing what…
arXiv:2608.17800v1 Announce Type: new Abstract: Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely…
arXiv:2509.12040v3 Announce Type: replace-cross Abstract: Open-Vocabulary Remote Sensing Image Segmentation (OVRSIS), an emerging task that adapts Open-Vocabulary Segmentation (OVS) to the remote sensing (RS) domain,…
arXiv:2511.16088v3 Announce Type: replace-cross Abstract: Traditional threat modeling remains reactive-focused on known TTPs and past incident data, while threat prediction and forecasting frameworks are often…
arXiv:2608.17262v1 Announce Type: cross Abstract: This paper considers robust nonadaptive regulation for general nonlinear systems in an output-feedback setting with arbitrarily high relative degree. We develop a…
arXiv:2604.12616v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) expand the attack surface of safety-aligned systems by coupling visual perception with text generation. Existing multimodal jailbreak…
arXiv:2510.08713v3 Announce Type: replace Abstract: Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular…
arXiv:2608.17017v1 Announce Type: cross Abstract: The implementation of artificial intelligence techniques and tools in the media will systematically and continuously alter their work and that of their professionals…
arXiv:2608.17202v1 Announce Type: new Abstract: Safety alignment in open-weight language models is trivially removable: abliteration projects a refusal-mediating direction out of the weights in minutes, and no…
arXiv:2608.17665v1 Announce Type: new Abstract: LLM-driven agents can autonomously exchange opinions on online platforms and form communities. Such agent-operated social platforms raise a new security concern: attackers…
arXiv:2608.17703v1 Announce Type: cross Abstract: Mobile robots that operate in side by side with humans and critical facilities must reach their goals at low cost, despite often unknown true traversal costs of the map…
arXiv:2509.15236v2 Announce Type: replace-cross Abstract: Data-driven surrogate models are increasingly used in computational fluid dynamics, and their reliability depends on the quality of the training data. These…
arXiv:2608.17393v1 Announce Type: new Abstract: Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integration, repository contexts, and execution feedback.…
arXiv:2608.17711v1 Announce Type: new Abstract: Prediction cascades significantly reduce energy consumption of Artificial Intelligence (AI) models while maintaining high predictive performance. The idea is that easy…
arXiv:2608.17170v1 Announce Type: new Abstract: Algorithm selection for constraint satisfaction problems requires extracting features that capture problem structure. Manually designing feature extractors demands deep…
arXiv:2608.17033v1 Announce Type: cross Abstract: Visual Place Recognition (VPR) aims to recognize the location of a query image by comparing it with a set of geo-referenced images. Although many datasets have been…
arXiv:2606.15315v2 Announce Type: replace Abstract: Personalized public transit routing in public transit systems remains challenging due to the difficulty of capturing and integrating diverse user preferences into…
arXiv:2602.23545v3 Announce Type: replace Abstract: In the real world, planning is often challenged by distribution shifts. As such, a model of the environment obtained under one set of conditions may no longer remain…
arXiv:2605.25477v2 Announce Type: replace-cross Abstract: The ability to efficiently and reliably learn new tasks has been a foundational challenge in robotics. Vision-Language-Action (VLA) models have demonstrated…
arXiv:2608.17270v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for scientific hypothesis generation. However, evaluating generated hypotheses remains a challenge for trustworthy…
arXiv:2608.17319v1 Announce Type: new Abstract: Browser agents perform well on short, clean demonstrations, but real deployment is fundamentally different: agents must sustain dozens of decisions on live websites while…
arXiv:2608.10448v2 Announce Type: replace Abstract: Multimodal emotion recognition in conversation (MERC) requires understanding complex interactions between verbal and non-verbal cues. However, most existing approaches…
arXiv:2608.17275v1 Announce Type: cross Abstract: AI agents increasingly act rather than merely read: across the Model Context Protocol (MCP) ecosystem, the share of deployed tools that modify external state has risen…
arXiv:2608.16977v1 Announce Type: new Abstract: AI systems are increasingly capable of contributing to mathematical research. In research practice, frontier-model reasoning is a limited resource, and expert mathematical…
