Skip to content
TILens What matters today in tech v0.0.5
Theme
Topics - AI
Browse
Calendar · AUG 2026
‹ Aug 2026 ›
  1. JAN
  2. FEB
  3. MAR
  1. APR
  2. MAY
  3. JUN
  1. JUL
  2. AUG
  3. SEP
  1. OCT
  2. NOV
  3. DEC
2
22 23
24 25 26 27 28 29 30
31
Favorites (0)

Daily edition · AI

The daily ledger

TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.

21 Aug 2026 edition
Python AI Django

Quoting Matt Webb

After I released version 1.0, I figured I would have to do the rotations myself. So I sat down with ChatGPT and I didn’t get it to write the code, but I got it to educate me. With a patient, interactive tutor, I was…

Source: Simon Willison's Weblog
AI Tools GitHub AI

langchain-ai/langchain: langchain-perplexity==1.4.1

Changes since langchain-perplexity==1.4.0 release(perplexity): 1.4.1 (#39826) fix(perplexity): include type="message" on Responses input items (#39774) fix(perplexity): preserve caller extra_body (#39203) chore: bump…

Source: LangChain Releases github-actions[bot]
AI Research AI

Reducing the Complexity of Matrix Multiplication by Quantum Computing

arXiv:2602.05541v3 Announce Type: replace-cross Abstract: Matrix multiplication is a fundamental operation in compute-intensive tasks and a key component of modern quantum acceleration frameworks. Here we present a…

Source: arXiv cs.LG Jiaqi Yao, Tianjian Huang, Tonghe Zhang, Ding Liu
AI Research AI

Clustering and Token Denoising for Faster and More Robust VLMs

arXiv:2608.19285v1 Announce Type: cross Abstract: Recent Visual-Language Models (VLMs) have enhanced the capabilities of pre-trained LLMs by adding vision tokens alongside text, with approaches like LLaVA showing…

Source: arXiv cs.LG Baptiste Rossigneux, Inna Kucher, Vincent Lorrain, Emmanuel Casseau
AI Research AI

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

arXiv:2608.20202v1 Announce Type: cross Abstract: Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions. However, existing memory…

Source: arXiv cs.LG Mengru Wang, Haozhe Luo, Zhenqian Xu, Zhixiang Cui, Haoming Xu, Qu Yang, Jizhan Fang, Junfeng Fang, Ningyu Zhang
AI Research AI

Learning Deterministic and Stochastic Forced Hamiltonian Systems

arXiv:2608.19688v1 Announce Type: cross Abstract: We develop a geometric framework for learning deterministic and stochastic forced Hamiltonian systems with neural networks. Motivated by the Lagrange-d'Alembert…

Source: arXiv cs.LG Benedikt Brantner, Tomasz Tyranowski
AI Research AI

Dynamic Structural Causal Modeling for Sleep

arXiv:2608.20285v1 Announce Type: new Abstract: The causal dynamics of sleep-disordered breathing are complex and vary across patient populations, hindering the development of targeted interventions. We learn dynamic…

Source: arXiv cs.LG Ranveer Singh, Saurabh Mathur, Pranuthi Tenali, Arun Badi, Sriraam Natarajan
AI Research AI

Active Inference as Context Acquisition for AI Agents

arXiv:2608.19202v1 Announce Type: cross Abstract: Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed…

Source: arXiv cs.LG Sanchayan Dutta, Sai Niranjan Ramachandran, Suvrit Sra
AI Research AI

Verifiably grounded machine interpretation of lunar geology

arXiv:2608.09276v2 Announce Type: replace-cross Abstract: Planetary geology relies on historical, interpretive reasoning to reconstruct past events from diverse observations. Here, we investigate how far this…

Source: arXiv cs.LG Tom Sander, Kay Wohlfarth, Christian W\"ohler
AI Research AI

RIPE++: Reinforced Keypoint Learning from Positive Pairs Only

arXiv:2608.19693v1 Announce Type: cross Abstract: Sparse keypoint extraction and matching underpin core tasks in geometric computer vision, including structure-from-motion, visual SLAM, augmented reality, and medical…

Source: arXiv cs.LG Johannes K\"unzel, Peter Eisert, Anna Hilsmann
AI Research AI

Projector Is All You Train

arXiv:2608.19726v1 Announce Type: cross Abstract: The typical training process of a multimodal large language model (MLLM) involves adapting both the language model backbone and the projector between the backbone and a…

Source: arXiv cs.LG Nyx Iskandar, Saathvik Selvan, Slater Victoroff
AI Research AI

End-to-end Early Classification of Time Series in Non-Stationary Environments

arXiv:2608.20044v1 Announce Type: new Abstract: Early Classification of Time Series (ECTS) requires making accurate decisions as early as possible in inherently online and evolving environments. Yet, most existing…

Source: arXiv cs.LG Aur\'elien Renault, Alexis Bondu, Antoine Cornu\'ejols, Vincent Lemaire
AI Research AI

SCAPE: Scenario-Conditioned Simulation-Augmented Policy Evaluation

arXiv:2608.19425v1 Announce Type: cross Abstract: Reliable performance evaluation is a central bottleneck for deploying robot-learning policies in real-world conditions. Real-world testing is faithful but costly and…

Source: arXiv cs.LG Dijie Zhu, Seunghun Oh, Ruopeng Huang, Zhiyu Huang, Jiaqi Ma, Chen Tang
AI Research AI

Spike-based Belief Propagation in Nonlinear Dynamical Systems

arXiv:2608.19907v1 Announce Type: cross Abstract: This paper presents a Bayesian control framework that integrates spike-based dynamics with probabilistic inference for adaptive control. Bayesian inference is widely…

Source: arXiv cs.LG Sepideh Adamiat, Hongye Wang, Wouter M. Kouw, Bert de Vries
AI Research AI

Towards On-Board Implementation of ML-Based Helicopter Weight Estimator

arXiv:2608.19210v1 Announce Type: new Abstract: This paper focuses on the implementation of a novel supervised Machine Learning model for estimating helicopter weight during takeoff, utilizing extensive datasets from…

Source: arXiv cs.LG Nicolas Valot, Ammar Mechouche, Benjamin Lesage, Claire Pagetti, Louis Fabre
AI Research AI

Auditing Cross-Lingual Fairness in Language Model Watermarking

arXiv:2608.20047v1 Announce Type: cross Abstract: Watermarking schemes for large language model output are evaluated almost exclusively on English text using each scheme's detection threshold and a narrow set of quality…

Source: arXiv cs.LG Alexander Nemecek, Osama Zafar, Debargha Ganguly, Vikash Singh, Vipin Chaudhary, Erman Ayday
AI Research AI

EnvHarness: Awakening Static Worlds for Agent Learning

arXiv:2608.19880v1 Announce Type: cross Abstract: LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it…

Source: arXiv cs.LG Chengsong Huang, Zifeng Wang, Rujun Han, Jun Yan, Yanfei Chen, Zoey CuiZhu, Ke Jiang, Peng Xia, Han Yu, Yufan Zhuang, Yifei Ming, Jiaqi Pan, Bhavana Dalvi Mishra, Jiaxin Huang, Burak Gokturk, Tomas P…
AI Research AI

Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models

arXiv:2608.20183v1 Announce Type: new Abstract: Classical information criteria such as the Bayesian Information Criterion (BIC) rely on regularity assumptions that break down for singular models, leading to incorrect…

Source: arXiv cs.LG Gr\'egoire Sergeant-Perthuis (CQSB, Sorbonne Universit\'e), Elias Tsigaridas (Ouragan Team, INRIA), Jules Tsukahara (Ouragan Team, INRIA)
AI Research AI

Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation

arXiv:2608.19611v1 Announce Type: cross Abstract: LLM reasoning is stochastic, and so understanding a model requires grappling with the distribution of reasoning chains that it might produce for a given question, i.e.,…

Source: arXiv cs.LG Eric Bigelow, Amir Zur, Satchel Grant, Tal Haklay, Can Rager, Owen Lewis, Thomas McGrath, Jack Merullo, Ekdeep Singh Lubana, Atticus Geiger
AI Research AI

skchange: Fast and Flexible Algorithms for Changepoint Detection

arXiv:2608.19767v1 Announce Type: cross Abstract: Skchange is an open-source Python library for detecting structural changes in time series. It implements modern change detection algorithms within a unified and…

Source: arXiv cs.LG Martin Tveten, Johannes Voll Kolst{\o}, Per August Jarval Moen
AI Research AI

Improved Confidence Estimates for Black-Box Large Language Models

arXiv:2608.19323v1 Announce Type: new Abstract: Uncertainty quantification (UQ) is essential for the safe deployment of large language models (LLMs). Existing methods, from verbalized confidence to ones requiring…

Source: arXiv cs.LG Sokhna Diarra Mbacke, Mouloud Belbahri, Gabriel Loaiza-Ganem
AI Research AI

Decoding silent reading from non-invasive EEG

arXiv:2608.20186v1 Announce Type: new Abstract: Non-invasive decoding of inner speech faces a fundamental data problem: a corpus pairing brain activity with a person's spontaneous inner monologue cannot be collected,…

Source: arXiv cs.LG Ingo Marquardt, Anthilia Alchanat, Priyanka Jain
AI Research AI

Concentrated Liquidity Provision: a Reinforcement Learning Perspective

arXiv:2608.19389v1 Announce Type: cross Abstract: Automated market makers (AMMs) are a cornerstone of decentralised finance (DeFi). Constant product markets with concentrated liquidity, such as UniswapV3, are now a…

Source: arXiv cs.LG Georgios Chionas, Charalampos Kleitsikas, Stefanos Leonardos, Leandro S\'anchez-Betancourt, Carmine Ventre
AI Research AI

Graphical Design of Interpretable Architectures

arXiv:2608.18936v2 Announce Type: replace Abstract: Designing, implementing, and comparing interpretable architectures requires a formal language to represent them. The most common representations fall short in one of…

Source: arXiv cs.LG Pietro Barbiero
AI Research AI

Information on trajectories: martingales and random times

arXiv:2608.20337v1 Announce Type: cross Abstract: Accounting for information flow on the path space of trajectories of a nonnegative martingale yields exact variational identities for it, even at arbitrary random times.…

Source: arXiv cs.LG Akshay Balsubramani
AI Research AI

Inadvertent Context Leakage in Language Models

arXiv:2608.19857v1 Announce Type: new Abstract: For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data. We study whether…

Source: arXiv cs.LG Jaiden Fairoze, Neal Mangaokar, Kamalika Chaudhuri, Sanjam Garg, Saeed Mahloujifar
AI Research AI

An Irreducible Quantum Advantage in Aligning World Models with Reality

arXiv:2608.19779v1 Announce Type: cross Abstract: World models provide digital simulacra of the true world, allowing agents to be trained and tested before costly real-world deployment. At each time step, they receive…

Source: arXiv cs.LG Josep Lumbreras, Hailan Ma, Jayne Thompson, Mile Gu
AI Research AI

A Neurosymbolic Approach for Explainable Early Diagnosis of Alzheimer's Disease

arXiv:2607.29530v2 Announce Type: replace Abstract: Identifying reliable Alzheimer's disease (AD) markers typically requires manual, labor-intensive transcription and expert analysis, limiting its scale. We introduce an…

Source: arXiv cs.LG Ranveer Singh, Pranuthi Tenali, Saurabh Mathur, Ameet Soni, Vaishali Phatak, Karla Lynch, Daniel Murman, Matthew Rizzo, Sriraam Natarajan
AI Research AI

A Layered Simplex Architecture for Large Alphabets

arXiv:2608.19908v1 Announce Type: cross Abstract: Probability estimation over large alphabets under log loss is a well-studied problem, with celebrated methods such as the Good-Turing estimator. We introduce and study a…

Source: arXiv cs.LG Meir Feder, Yaniv Fogel, Ruediger Urbanke
AI Research AI

RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations

arXiv:2608.19735v1 Announce Type: new Abstract: We introduce RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation. RecPFN is pretrained entirely on synthetic clickstream…

Source: arXiv cs.LG En Zhi Tan, Jia Xiang Lim, Bryan Lijie Chew, Tze Minh Ng, Benjamin Yan Han Yap
AI Research AI

A Locally Tokenized Generative Model for Robust Time-Series Watermarking

arXiv:2608.19727v1 Announce Type: new Abstract: Watermarking is a central tool for provenance in generative models, yet its application to multivariate time series remains hindered by reliability failures under…

Source: arXiv cs.LG Dongbin Kim, Geonwoo Shin, Yujin Choi, Soyeon Park, Jaewook Lee
AI Research AI

Multi-Source Wasserstein Distributionally Robust Graph Learning

arXiv:2608.19914v1 Announce Type: new Abstract: Network topology inference from graph signals is central to graph signal processing with applications in neuroscience, sensor, and social networks. In practice,…

Source: arXiv cs.LG Chuansen Peng, Yifan Xia, Jinshan Zhong, Xiaojing Shen
AI Research AI

The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction

arXiv:2605.29411v2 Announce Type: replace Abstract: Under standard graphical assumptions, the Markov boundary of a target variable is the smallest set of features that renders every other feature redundant. Once the…

Source: arXiv cs.LG Shu Wan, Abhinav Gorantla, Huan Liu, K. Sel\c{c}uk Candan
AI Research AI

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

arXiv:2608.15949v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have enabled their use as conversational recommender systems (CRS), demonstrating strong recommendation accuracy…

Source: arXiv cs.LG Cedar Site Bai, Zhenyu Liao, Duanshun Li, Sheikh Sarwar, Huiyuan Chen, Yuan Chen, Changhe Yuan, Haiyang Zhang, Qilin Qi
AI Research AI

Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation

arXiv:2608.19890v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) methods aim to bridge the domain gap between the source and target domains. However, traditional TTA methods become ineffective when the label…

Source: arXiv cs.LG Jia-Qi Lin, Yuangang Pan, Chang-Dong Wang, Haizhang Zhang, Ivor W. Tsang, Joey Tianyi Zhou
AI Research AI

Quantifying Event Impacts on Time Series via Multiscale Contrastive Learning

arXiv:2608.19447v1 Announce Type: new Abstract: Shocks that spread through the web, such as cybersecurity breach disclosures, can abruptly disrupt financial time series and cause substantial abnormal losses. While these…

Source: arXiv cs.LG Yiming Sun, Shengyu Chen, Zhengzhang Chen, Haoyu Wang, Xiaowei Jia, Haifeng Chen
AI Research AI

PETA:Parameter-Efficient Test-Time Adaptation for Virtual Screening

arXiv:2608.19906v1 Announce Type: new Abstract: Accurately ranking active ligands for a target protein pocket from massive chemical libraries remains a central challenge in virtual screening. DrugCLIP and its recent…

Source: arXiv cs.LG Jia-Qi Lin, Yinghua Yao, Chang-Dong Wang, Yew-Soon Ong, Yuangang Pan
AI Research AI

Provably Efficient Self-Calibrating Quantum Fault Tolerance

arXiv:2608.05686v2 Announce Type: replace-cross Abstract: Quantum error correction protects logical information only when every physical operation remains below the fault-tolerance threshold, a condition that must be…

Source: arXiv cs.LG Weiyuan Gong, Hong-Ye Hu
AI Research AI

GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows

arXiv:2606.00140v3 Announce Type: replace Abstract: While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and…

Source: arXiv cs.LG Jonas Henry Grebe, Tobias Braun, Anna Rohrbach, Marcus Rohrbach
AI Research AI

Triangular Fuzzy Rescaling Distance

arXiv:2608.19234v1 Announce Type: new Abstract: Decision-making in complex systems often involves dealing with imprecise or uncertain information, frequently represented using fuzzy sets, particularly Triangular Fuzzy…

Source: arXiv cs.LG Eddy Soria, Aida Valls, Ana Beatriz Hern\'andez-Lara
AI Research AI

Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection

arXiv:2608.19858v1 Announce Type: new Abstract: Generalizable dynamic graph anomaly detection (DGAD) enables pretrained detectors to identify anomalies in unseen target domains without costly retraining. However,…

Source: arXiv cs.LG Jialun Zheng, Hanchen Yang, Jiannong Cao, Yankai Chen, Yuanjing Feng, Philip S. Yu
AI Research AI

MulTTiPop: A Multitrack Transcription Dataset for Pop Music

arXiv:2607.08756v2 Announce Type: replace-cross Abstract: We present MulTTiPop, a dataset of pop music segments and their associated multitrack MIDI recordings for the evaluation of automatic music transcription models.…

Source: arXiv cs.LG Nathan Pruyne, Benjamin Stoler, William Chen, Chien-yu Huang, Shinji Watanabe, Chris Donahue
AI Research AI

Physical-Support Confidence Sets for Highly Coherent Dictionaries

arXiv:2608.20295v1 Announce Type: new Abstract: Sparse pursuit after dictionary learning can yield a precise atom support even when its physical interpretation is not justified by the calibration data, especially for…

Source: arXiv cs.LG Guan-Ju Peng
AI Research AI

LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages

arXiv:2608.11922v2 Announce Type: replace-cross Abstract: Predictive-distribution entropy is a strong answer-selection rule in retrieval-augmented generation (RAG) for question answering: across five QA benchmarks,…

Source: arXiv cs.LG Hung-Chun Hsu, Po-Jen Ko, Che-Cheng Wu, Li-Yang Chang, Chuan-Ju Wang
AI Research AI

Deep neural networks as lattice gauge theories

arXiv:2608.19331v1 Announce Type: cross Abstract: We modify the NN/QFT duality [1] to incorporate the layerwise permutation symmetry of the network, resulting in a $(0\!+\!1)$-dimensional lattice gauge theory, in which…

Source: arXiv cs.LG Ro Jefferson, Shradha Ramakrishnan
AI Research AI

LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection

arXiv:2608.19463v1 Announce Type: new Abstract: Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations.…

Source: arXiv cs.LG Tu Anh Hoang Nguyen, Dang Nguyen, Thuc Duy Le, Trung Le, Sunil Gupta
AI Research AI

Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress

arXiv:2608.19408v1 Announce Type: cross Abstract: On-policy distillation (OPD) has emerged as an effective framework for post-training language models by pairing student-generated trajectories with dense token-level…

Source: arXiv cs.LG Chen Yang, Haiyuan Wan, Rengrong Xiong, Yize Chen, Danny H. K. Tsang
AI Research AI

Empirical Characterization of Learning Geometry in Hybrid Quantum Forecasting Models

arXiv:2608.19497v1 Announce Type: new Abstract: We characterize the learning dynamics of a compact hybrid quantum forecasting model through comparison with a structurally aligned classical baseline. Using stationary…

Source: arXiv cs.LG Sandra Leticia Ju\'arez-Osorio, Jorge I. Hernandez-Martinez, Jesus Ivan Ruiz-Martinez, Andres Mendez-Vazquez, Eduardo Rodriguez-Tello
AI Research AI

Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning

arXiv:2608.19836v1 Announce Type: new Abstract: Probabilistic shielding is a technique for safe reinforcement learning (RL). Typically, a static observer -- called the shield -- constrains the learning agent's actions…

Source: arXiv cs.LG Astrid Horn Brorholt (Aalborg University, Aalborg, Denmark), Maris F. L. Galesloot (Radboud University, Nijmegen, Netherlands), Nils Jansen (Radboud University, Nijmegen, Netherlands), Kim Guldstrand…
AI Research AI

VQC-ZTI: Variational Quantum Control for Zero Trust Protection of the Tactile Internet

arXiv:2608.18572v1 Announce Type: cross Abstract: Tactile Internet services couple cyber events directly to physical actuation, so security decisions must improve risk discrimination without perturbing the control path.…

Source: arXiv cs.LG Mubassir Serneabat Sudipto (Iowa State University), Shakil Ahmed (Grand Valley State University), Ashfaq Khokhar (Kansas State University)
AI Research AI

AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement

arXiv:2608.20318v1 Announce Type: cross Abstract: Recursive self-improvement (RSI) asks whether an AI system can improve the process that produces AI systems, so that the next system inherits the improvement. That…

Source: arXiv cs.LG Yizhe Chi, Wenyi Li, Deyao Hong, Xiaoqiu Wang, Mingju Gao, Kaisen Yang, Bingxiang He, Youjie Zheng, Calvin Xiao, Qinhuai Na
AI Research AI

Orthogonal JEPA: Factorized Predictive States for Latent World Models

arXiv:2608.20065v1 Announce Type: new Abstract: World models construct latent states that support prediction, planning, and reasoning about an underlying system. Joint-embedding predictive architectures (JEPAs) offer a…

Source: arXiv cs.LG Taoyong Cui, Pheng Ann Heng, Wanli Ouyang
AI Research AI

Quantum Gaussian processes for prediction of channel observations

arXiv:2608.19306v1 Announce Type: cross Abstract: Given a set of input states, we consider the task of predicting the expectation value of a Pauli observable at the output of an unknown quantum evolution, using only a…

Source: arXiv cs.LG Jonas J\"ager, Yaroslav Khmelnitskiy, Paolo Braccia, Artur Miroszewski, Diego Garc\'ia-Mart\'in, M. Cerezo, Piotr Czarnik
AI Research AI

Interpretable Feature Learning for RF Fingerprinting via Polar MKANs

arXiv:2608.19881v1 Announce Type: cross Abstract: Radio frequency (RF) fingerprinting authenticates wireless devices from hardware-induced I/Q impairments, typically with deep learning feature extractors that are…

Source: arXiv cs.LG Mikhail Krasnov, Ljupcho Milosheski, Carolina Fortuna
AI Research AI

Maximum Likelihood Reinforcement Learning

arXiv:2602.02710v2 Announce Type: replace Abstract: Reinforcement learning (RL) is the method of choice for training models in setups where the objective function can only be evaluated by sampling from the model. Our…

Source: arXiv cs.LG Fahim Tajwar, Guanning Zeng, Yueer Zhou, Yuda Song, Daman Arora, Yiding Jiang, Jeff Schneider, Ruslan Salakhutdinov, Haiwen Feng, Andrea Zanette
AI Research AI

Longitudinal Bayesian Learning of Continuous Disease Position across the Alzheimer's Disease Continuum

arXiv:2608.19436v1 Announce Type: new Abstract: Alzheimer's disease (AD) progresses as a continuous biological process, whereas most existing neuroimaging-based artificial intelligence methods remain limited to discrete…

Source: arXiv cs.LG Yingying Zhang, Kun Zhao, Guodong Liu, Qi Huang, Pengfei Gu, Dongchul Kim, Erik Enriquez, Alex D. Leow, Paul M. Thompson, Heng Huang, Hongchang Gao, Liang Zhan, Haoteng Tang
AI Research AI

Flow Matching Meets 3D Curvilinear Structure Segmentation in Medical Imaging

arXiv:2608.19965v1 Announce Type: cross Abstract: Segmentation of curvilinear anatomical structures in 3D medical images remains challenging due to complex topology, severe class imbalance, weak contrast, and large…

Source: arXiv cs.LG Sidi Mohamed Sid'El Moctar, Nicolas Vitry, H\'el\`ene Bouvrais
AI Research AI

Ask Self, Ask Others: Relation Is All You Need

arXiv:2608.20172v1 Announce Type: new Abstract: Attention directly derives normalized information flow from pairwise scores. We introduce Relation, an alternative token-mixing primitive that first organizes pairwise…

Source: arXiv cs.LG Yuting Ge, Pengju Yang, Mingkai Nie
AI Research AI

Answer-Level Trust Selection for Physical Vision-Language Reasoning

arXiv:2608.19807v1 Announce Type: new Abstract: Vision-language models (VLMs) can estimate physical quantities such as duration, speed, and acceleration from visual observations, but existing benchmarks primarily assess…

Source: arXiv cs.LG Rongyu Yu, Ke Niu, Fengxiang He
AI Research AI

A comparison between ceiling-mounted FMCW, IR-UWB and Wi-Fi radar for in-bedroom human activity monitoring and sleep interruption detection

arXiv:2608.20322v1 Announce Type: new Abstract: Despite their growing importance for contact-free radio frequency (RF) based healthcare monitoring, different radio technologies such as frequency-modulated continuous…

Source: arXiv cs.LG Anton Lambrecht, Reda El Hail, Xianjun Jiao, Pieter Crombez, Dominique Schreurs, Peter Karsmakers, Adnan Shahid, Eli De Poorter
AI Research AI

Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis

arXiv:2608.19297v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) excel in medical applications, most of them favor static images or short-term signals. In the critical field of dynamic…

Source: arXiv cs.LG Yihan Xie, Hanwen Cui, Runze Ye, Juekai Lin, Haoyang Wang, Jinhao Mao, Bo Zhang, Wenqiao Zhang, Xiaogang Guo, Jun Xiao, Lei Zhang
AI Research AI

Graph Machine: Exploring Edge Mechanisms as an Inductive Bias

arXiv:2608.06834v2 Announce Type: replace Abstract: Transformers provide a powerful architecture for global content-based matching, but reasoning problems may benefit from a stronger inductive bias toward iterative…

Source: arXiv cs.LG Lintai Hou
AI Research AI

DICS: Data-Informed Centroid Splitting for Decision Tree Classifiers

arXiv:2608.20258v1 Announce Type: new Abstract: Decision tree-based models are widely used in machine learning due to their interpretability and strong empirical performance. However, training decision trees can be…

Source: arXiv cs.LG MD Saifur Rahman Mazumder, Feng Yu
AI Research AI

From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems

arXiv:2605.23955v3 Announce Type: replace-cross Abstract: Deploying machine learning in regulated financial environments -- credit risk, fraud detection, and anti-money laundering -- exposes critical vulnerabilities in…

Source: arXiv cs.LG Ruizhe Zhou, Xiaoyang Liu, Gaoyuan Du, Yi Zheng, Shouxi Ren, Deepayan Chakrabarti, Dengdu Jiang
AI Research AI

GraphPFN: A Prior-Data Fitted Graph Foundation Model

arXiv:2509.21489v4 Announce Type: replace Abstract: Graph foundation models face several fundamental challenges including transferability across diverse domains and data scarcity, which calls into question the very…

Source: arXiv cs.LG Dmitry Eremeev, Oleg Platonov, Gleb Bazhenov, Artem Babenko, Liudmila Prokhorenkova
AI Research AI

Quantum Kernel Estimation for the Discovery of Early Lung Cancer Detection

arXiv:2608.19304v1 Announce Type: new Abstract: Lung cancer screening with low-dose chest computed tomography reduces mortality, but its impact is limited by uptake, adherence, and management challenges. Blood-based…

Source: arXiv cs.LG Hamed Javidi, Alex Zajichek, Hakan Doga, Laxmi Parida, Filippo Utro, Peter J. Mazzone
AI Research AI

Feature Evolution and Migration during Vision Transformer Training

arXiv:2608.20134v1 Announce Type: cross Abstract: We present a novel view on feature evolution in Vision Transformers (ViTs) by visualizing the training process over two dimensions -- network depth (layer) and training…

Source: arXiv cs.LG Joonas J\"arve, Halil Ibrahim Aysel, Tarun Khajuria, Meelis Kull
AI Research AI

Recovering Nonlinear Functions of Latent Variables: A Plausible-Value Neural Network Framework

arXiv:2608.19282v1 Announce Type: cross Abstract: When factor scores replace true latent scores in nonlinear prediction, measurement error attenuates the recoverable variance of any $k$th-order component of the…

Source: arXiv cs.LG Eunjeong Song (Department of Education, Korea University, Seoul, Republic of Korea), Sehee Hong (Department of Education, Korea University, Seoul, Republic of Korea)
AI Research AI

Learning piecewise-smooth dynamical systems

arXiv:2608.19785v1 Announce Type: cross Abstract: Discovering dynamical systems from trajectory data is a central problem in applied mathematics and engineering. Whilst recent advances in machine learning have led to…

Source: arXiv cs.LG Davide Murari, Erik Jansson, Chris Budd OBE, Carola-Bibiane Sch\"onlieb
AI Research AI

Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo

arXiv:2608.20123v1 Announce Type: cross Abstract: We study inference-time control for text generation in discrete diffusion language models, where the goal is to steer sampling toward sequence-level rewards without…

Source: arXiv cs.LG Lohithsai Yadala Chanchu, Hany Abdulsamad, Christian A. Naesseth
AI Research AI

Uncovering the Limits of Proof Sharing for Neural Networks

arXiv:2608.19351v1 Announce Type: new Abstract: Robustness verification of neural networks is increasingly important, due to their use in many critical domains. In certain scenarios, proof sharing has been shown to…

Source: arXiv cs.LG Kanak Das, Shubham Ugare, Bor-Yuh Evan Chang, Sasa Misailovic, Gagandeep Singh, Manu Sridharan
AI Research AI

CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting

arXiv:2608.20025v1 Announce Type: new Abstract: Probabilistic forecasting models are widely used for time series forecasting in domains such as energy systems, finance, medicine, and transportation. In recent years,…

Source: arXiv cs.LG Alexander Marusov, Dmitry Anikin, Petr Sokerin, Vitaliy Pozdnyakov, Ilya Kuleshov, Alexey Zaytsev
AI Research AI

SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events

arXiv:2608.20117v1 Announce Type: new Abstract: The emergence of large-scale Weather and Climate (W&C) datasets offers new opportunities for modeling extreme Earth events (ExEE) and their impacts using deep learning.…

Source: arXiv cs.LG Hugo Porta, Emanuele Dalsasso, Chang Xu, Theo Gnassounou, Devis Tuia
AI Research AI

Why AI Detection Fails for Academic Integrity

arXiv:2608.11256v2 Announce Type: replace Abstract: Institutions use commercial AI detectors for academic integrity, yet detectors cannot distinguish AI editing from full LLM drafts and may treat both as misconduct. In…

Source: arXiv cs.LG Jonathan A. Karr Jr, Grigorii Khvatskii, Ting Hua, Nitesh V. Chawla
AI Research AI

Continuous Adversarial MeanFlow Transfer

arXiv:2608.19540v1 Announce Type: new Abstract: Training fast generators on new domains with limited data remains challenging for two reasons. First, adapting a pretrained diffusion or flow model to a new domain leaves…

Source: arXiv cs.LG Yara Bahram, Zahra Dehghani, M\'elodie Desbos, Eric Granger, Pablo Piantanida, Mohammadhadi Shateri
AI Research AI

Unsupervised Anomaly Detection Using Flow Matching on Tabular Data

arXiv:2608.19801v1 Announce Type: new Abstract: Financial anomaly detection often relies on large unlabeled transaction logs, where anomalous samples may already be present during training. Such training-set…

Source: arXiv cs.LG Philip Konz, Tejaswini Medi, Margret Keuper
AI Research AI

FinVerse: Financial Time-Series Benchmark

arXiv:2608.03259v2 Announce Type: replace Abstract: As time-series foundation models have emerged, the need for benchmarks that can evaluate their forecasting ability in meaningful ways has become increasingly…

Source: arXiv cs.LG Jaehoon Lee, Jun Seo, Seunghan Lee, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Minjae Kim, Sungdong Yoo, Junhyeok Kang, Sangjun Han, Soonyoung Lee, Wonbin Ahn
AI Research AI

Transfer Learning in Nonparametric Regression with Deep ReLU Networks

arXiv:2608.20255v1 Announce Type: cross Abstract: This paper develops a general transfer learning framework for nonparametric regression with data consisting of multiple groups. Under the assumption that groups share a…

Source: arXiv cs.LG Junpeng Ren, Carlos Misael Madrid Padilla, Yanzhen Chen, Oscar Hernan Madrid Padilla
AI Research AI

TorchDCM: A Unified PyTorch-Native Package for Discrete Choice Modeling

arXiv:2608.19231v1 Announce Type: cross Abstract: Estimating large and simulation-intensive discrete choice models (DCMs) requires repeated evaluation of utilities, probabilities, derivatives, and simulated likelihoods…

Source: arXiv cs.LG Baichuan Mo, Zhengzhong Ricky You, Xiqun Michael Chen, Ruimin Li
AI Research AI

A Standardized Framework for Machine Learning in Power System Protection

arXiv:2608.20181v1 Announce Type: new Abstract: Studies of machine-learning-based power-system protection increasingly report near-perfect scores, yet the meaning of those scores depends strongly on the evaluation…

Source: arXiv cs.LG Julian Oelhaf, Georg Kordowich, Paula Andrea P\'erez-Toro, Christian Bergler, Johann J\"ager, Andreas Maier, Siming Bayer
AI Research AI

RepSelect: Robust LLM Unlearning via Representation Selectivity

arXiv:2606.17168v3 Announce Type: replace Abstract: When LLM weights are open or fine-tuning is available through an API, suppressing hazardous knowledge and tendencies is not enough: removal has to be deep enough that…

Source: arXiv cs.CL Filip Sondej, Yushi Yang, Adam Mahdi
AI Research AI

HealMed: Multilingual Evaluation of Large Language Models in Medicine

arXiv:2608.19981v1 Announce Type: new Abstract: We present HealMed, an expert-reviewed benchmark for multilingual evaluation of large language models in medicine. HealMed contains 1,000 examples in each of nine…

Source: arXiv cs.CL Yingjian Chen (Drew), Fan Gao (Drew), Sherry T. Tong (Drew), Haoyu Zhang (Drew), Aosong Feng (Drew), Kevin W. Jin (Drew), Xing Wu (Drew), Jinghui Lu (Drew), Abdul Samad (Drew), Akbar Faruqi (Drew), C…
AI Research AI

Can Agent Memory Systems Track Evolving State?

arXiv:2608.19652v1 Announce Type: cross Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps. While existing memory benchmarks focus largely…

Source: arXiv cs.CL Xinyi Fan, Miri Liu, Ruozhen Yang, Siru Ouyang, Jiawei Han
AI Research AI

ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism

arXiv:2508.00554v5 Announce Type: replace-cross Abstract: In financial trading, large language model (LLM)-based agents demonstrate significant potential, but their decisions can be sensitive to noisy and non-stationary…

Source: arXiv cs.CL Li Zhao, Rui Sun, Zuoyou Jiang, Bo Yang, Yuxiao Bai, Mengting Chen, Jing Li, Zuo Bai
AI Research AI

ContractScrub: A benchmark for final review of legal contracts

arXiv:2608.20204v1 Announce Type: cross Abstract: Legal work, with its heavy reliance on processing large amounts of text, is often considered one of the domains most exposed to the use of LLMs. Contract ``scrubbing,''…

Source: arXiv cs.CL Yejin Bang, Kirsty Fielding, Brandan Oliver, Brian Birke, Nabeel Seedat, Andrew M. Bean
AI Research AI

Learning how to Forget: Fine-tuning for Long-Context Sparse Attention

arXiv:2608.19920v1 Announce Type: new Abstract: A lot of prior work addressed key-value (KV) cache selection and compression by sparse attention to enable long-context inference for transformer language models without…

Source: arXiv cs.CL Matthias Seeger, Zeyu Zhang, Vihang Patil, Konstantinos Benidis, Sebastian Schelter
AI Research AI

Inducing Task Models from Computer-Use Traces

arXiv:2608.20319v1 Announce Type: new Abstract: Naturalistic computer-use traces, passively recorded screenshots and mouse or keyboard actions, are a valuable resource for deriving symbolic, auditable, and reusable…

Source: arXiv cs.CL Yucheng Jiang, Zora Zhiruo Wang, Ruishi Chen, Diyi Yang
AI Research AI

Qworld: Question-Specific Evaluation Criteria for LLMs

arXiv:2603.23522v2 Announce Type: replace Abstract: Evaluating large language models (LLMs) on open-ended questions is difficult because response quality depends on the question's context. Binary scores and static…

Source: arXiv cs.CL Shanghua Gao, Yuchang Su, Pengwei Sui, Curtis Ginder, Marinka Zitnik
AI Research AI

An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction

arXiv:2608.20320v1 Announce Type: cross Abstract: Travel behavior research increasingly combines digital data collection with predictive modeling, yet these stages are often developed and evaluated separately. This…

Source: arXiv cs.CL Narges Ahmadi (McGill University), Yubo Jiao (McGill University), J\^onatas Augusto Manzolli (McGill University), Jiangbo Yu (McGill University), Luis Miranda-Moreno (McGill University)
AI Research AI

Robust Incomplete Multimodal Sentiment Analysis via Iterative Proxy Correction

arXiv:2608.19971v1 Announce Type: new Abstract: Multimodal sentiment analysis aims to infer affective states by integrating language, visual, and acoustic cues. However, real-world multimodal inputs are often incomplete…

Source: arXiv cs.CL Zhifa Geng, Subin Huang, Hao Guo, Junjie Chen, Sanmin Liu, Chao Kong
AI Research AI

SPyCE: Skill-Policy Co-evolution for Multimodal Agents

arXiv:2607.13854v2 Announce Type: replace Abstract: Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps. Existing reinforcement learning methods reduce…

Source: arXiv cs.CL Ru Zhang, Weijie Qiu
AI Research AI

Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories

arXiv:2608.19621v1 Announce Type: new Abstract: Large language models (LLMs) offer a scalable approach to social simulation, but their credibility depends on how agents are constructed. Existing methods can partially…

Source: arXiv cs.CL Hexi Wang, Yujia Zhou, Bangde Du, Weihang Su, Xinyuan Cao, Qingyi Pan, Qingyao Ai, Yueyue Wu, Min Zhang, Yiqun Liu
AI Research AI

Does Listening Matter? Backchanneling and Nodding in AI Clone

arXiv:2608.19527v1 Announce Type: cross Abstract: AI clones that imitate a specific person typically reproduce what the person says and how they sound, but not how they listen. We investigate whether adding multimodal…

Source: arXiv cs.CL Koji Inoue, Kazushi Kato, Tatsuya Kawahara, Shunichi Kasahara
AI Research AI

Phantom Gains: Auditing Self-Improvement Against a Measured Null

arXiv:2608.20290v1 Announce Type: cross Abstract: Whether a language model has improved itself is increasingly judged not by mean accuracy but by which individual problems it gains and loses. Tracking these transitions…

Source: arXiv cs.CL Cheng Xu, Nan Yan, Liming Chen, M-Tahar Kechadi
AI Research AI

Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA

arXiv:2604.13731v2 Announce Type: replace Abstract: Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free…

Source: arXiv cs.CL Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai
AI Research AI

The Asymmetric Harms of LLM Compression

arXiv:2608.19670v1 Announce Type: new Abstract: Large language models (LLMs) compression reduces deployment costs, but standard aggregate metrics like perplexity and accuracy often mask underlying behavioral shifts. In…

Source: arXiv cs.CL Yuan Wu, Mairui Li, Lesia Semenova, Chudi Zhong
AI Research AI

Stopping and Routing LLM Judge Panels

arXiv:2608.19802v1 Announce Type: new Abstract: LLM evaluation pipelines often have many candidate judges: general LLM-as-a-judge prompts, reward models, safety classifiers, confidence variants, and task-specific…

Source: arXiv cs.CL Bin Zhu, Yi Xie, Yanghui Rao
AI Research AI

EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation

arXiv:2604.26170v2 Announce Type: replace Abstract: Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge. Such adaptation often requires iteratively…

Source: arXiv cs.CL Ting-Wei Li, Sirui Chen, Jiaru Zou, Yingbing Huang, Tianxin Wei, Jingrui He, Hanghang Tong
AI Research AI

Reliable Financial Named Entity Recognition under Domain Shift

arXiv:2608.19558v1 Announce Type: new Abstract: Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, while standard F1 scores…

Source: arXiv cs.CL Zihao Zheng, Baichuan Li, Junyi Yao, Jiayu Long
AI Research AI

Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does

arXiv:2608.19515v1 Announce Type: new Abstract: Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged. Yet…

Source: arXiv cs.CL Xinyi Liu, Hooshang Nayyeri, Dilek Hakkani-Tur, Emine Yilmaz, JK Kim, Yifei Zhang, Charith Peris, Hari Thadakamalla
AI Research AI

SABET-QA: Temporal Knowledge Graph Question Answering

arXiv:2608.20083v1 Announce Type: new Abstract: Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step…

Source: arXiv cs.CL Brahim Touayouch, Mirette Moawad, Dmitry Akulov
AI Research AI

FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving

arXiv:2608.19758v1 Announce Type: new Abstract: Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the…

Source: arXiv cs.CL Qihang Fan, Huaibo Huang, Zhiying Wu, Bingning Wang, Ran He
AI Research AI

Self-Harness: Harnesses That Improve Themselves

arXiv:2606.09498v3 Announce Type: replace Abstract: The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Because different…

Source: arXiv cs.CL Hangfan Zhang, Shao Zhang, Kangcong Li, Chen Zhang, Yang Chen, Yiqun Zhang, Lei Bai, Shuyue Hu
AI Research AI

A Finite-Calibration Regime Map for LLM Judge Panels

arXiv:2606.01034v2 Announce Type: replace Abstract: Deploying an LLM judge panel spends human labels on fitting a calibrator, constructing candidate judge paths, and validating which candidate to deploy. We study when…

Source: arXiv cs.CL Bin Zhu, Yi Xie, Yanghui Rao
AI Research AI

When Text and Numbers Disagree: Evidence Arbitration in Large Language Models

arXiv:2608.20116v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in settings where textual summaries, numerical observations, and external tool outputs may provide conflicting evidence.…

Source: arXiv cs.CL Mattia Carletti, Edward Phillips, Fredrik K. Gustafsson, Patitapaban Palo, Lei Clifton, Danielle Belgrave, Xiao Gu, David A. Clifton
AI Research AI

Outcome Monitors: Recovery Affordances for Silent Tool Failures

arXiv:2608.19303v1 Announce Type: cross Abstract: When a tool call times out, the agent sees the failure and can route around it. A cached error page or negative price can instead arrive in the expected format and be…

Source: arXiv cs.CL Sugam Panthi, Rabab Abdelfattah
AI Research AI

Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents

arXiv:2608.20274v1 Announce Type: cross Abstract: Large language model (LLM) agents can induce skills from completed tasks and reuse them later to grow more capable with experience. In practice, induced skills may…

Source: arXiv cs.CL Yiyang Feng, Biddut Sarker Bijoy, Niranjan Balasubramanian, Jiawei Zhou
AI Research AI

PersonalBench: Measuring the Authorship Gap in LLM Personalization

arXiv:2608.19746v1 Announce Type: new Abstract: Personalized text generation aims to make LLMs write in a specific individual's style, yet existing benchmarks measure task accuracy or preference alignment rather than…

Source: arXiv cs.CL Yash Ganpat Sawant
AI Research AI

A Virtual Member of a Community of Practice for the Society of Petroleum Engineers: From Prototype to Deployment

arXiv:2608.19199v1 Announce Type: new Abstract: We describe the evolution of a virtual assistant, called ATHENA, designed to support the capture, retrieval, and dissemination of knowledge for members of a Community of…

Source: arXiv cs.CL John Boden, Joshua Eckroth, Dayne Freitag, Skyler Gipson, Johnathan Keefe, Karen Myers, Eric Schoen, Pedro Sequeira, Reid Smith, Michael Wessel
AI Research AI

Are LLMs becoming similarly creative? Evidence from three years of models

arXiv:2608.19437v1 Announce Type: new Abstract: Many benchmarks track Large Language Model (LLM) performance on tasks with verifiable answers, but less is known about how LLM performance is evolving on open-ended tasks,…

Source: arXiv cs.CL Nirav Patel, Josiah Crossman, Eva Aggarwal, Emily Wenger
AI Research AI

StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary

arXiv:2608.19723v1 Announce Type: cross Abstract: Streaming video understanding requires models to causally update state as video arrives and organize growing history into semantic units that can evolve, persist, and be…

Source: arXiv cs.CL Chenxi Shao, Bozhong Wang, Jiaxin Huang, Zhao Liu, Sunwei Zhu, Tianxin Hang, Gaoqi He, Yang Li, Changbo Wang
AI Research AI

GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval

arXiv:2608.18752v2 Announce Type: replace-cross Abstract: Statutory retrieval is necessary for citation-grounded legal question answering, but remains underexplored for Greek. We introduce GreekBarRetrieval, a public…

Source: arXiv cs.CL Ernest Beta, Odysseas S. Chlapanis, Dimitrios Galanis, Ion Androutsopoulos
AI Research AI

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

arXiv:2608.19799v1 Announce Type: new Abstract: Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program behavior but also…

Source: arXiv cs.CL Zhipeng Xu, Jiahao Lu, Yining Zheng, Yuxin Wang, Xipeng Qiu
AI Research AI

SynFlow: A Multidimensional Diachronic Semantic Analysis Toolkit

arXiv:2608.19472v1 Announce Type: new Abstract: Lexical semantic change (LSC) is commonly modelled through vector-space representations, but these approaches often provide limited insight into which aspects of usage are…

Source: arXiv cs.CL Bach Phan-Tat, Kris Heylen, Dirk Geeraerts, Stefano De Pascale, Dirk Speelman
AI Research AI

TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning

arXiv:2510.03519v3 Announce Type: replace Abstract: Time series reasoning is crucial to decision-making in diverse domains, including finance, energy, and scientific discovery. While existing time series foundation…

Source: arXiv cs.CL Fangxu Yu, Hongyu Zhao, Tianyi Zhou
AI Research AI

HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings

arXiv:2502.15411v5 Announce Type: replace Abstract: Accurate tagging of earnings reports can yield significant short-term returns for stakeholders. The machine-readable inline eXtensible Business Reporting Language…

Source: arXiv cs.CL Rasmus T. Aavang, Giovanni Rizzi, Rasmus Tjalk-B{\o}ggild, Alexandre Iolov, Mike Zhang, Johannes Bjerva
AI Research AI

One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows

arXiv:2608.19741v1 Announce Type: new Abstract: Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling. Yet completing…

Source: arXiv cs.CL Zhuochun Li, Youngmin Ko, Ali Keramati, Nicola Ferri, Susana Palmaz Lopez Pelaez, Liang-Chun Tsai, Calvin Wang, Mirco Milletari, Tuhin Kundu, Vadim Smolyakov, Kjartan Olafsson, Tommy Guy
AI Research AI

Automatic bioinformatic software named entity recognition from literature

arXiv:2608.19201v1 Announce Type: new Abstract: Bioinformatics software and databases are essential components of modern life science research, yet their mentions in the scientific literature are often inconsistent and…

Source: arXiv cs.CL Hao Xuan, Rithvij Pasupuleti, Ben Liu, Haishuo Sun, Jun Zhang, Zijun Yao, Cuncong Zhong
AI Research AI

Towards Audio Token Compression in Large Audio Language Models

arXiv:2511.20973v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) deliver strong performance across speech and audio tasks, but their audio encoders generate high-rate token sequences (e.g.,…

Source: arXiv cs.CL Saurabhchand Bhati, Samuel Thomas, Hilde Kuehne, Rogerio Feris, James Glass
AI Research AI

Every Step of the Way: Video-based Parkinsonian Turning Step Counting

arXiv:2606.27918v2 Announce Type: replace-cross Abstract: As a prominent symptom of Parkinson's disease (PD), turning impairment is evaluated through parameters such as turning angle, duration, and particularly, the…

Source: arXiv cs.AI Qiushuo Cheng, Jingjing Liu, Catherine Morgan, Alan Whone, Majid Mirmehdi
AI Research AI

WaveVerif: Acoustic Side-Channel based Verification of Robotic Workflows

arXiv:2510.25960v2 Announce Type: replace-cross Abstract: In this paper, we present a framework that uses acoustic side-channel analysis (ASCA) to monitor and verify whether a robot correctly executes its intended…

Source: arXiv cs.AI Zeynep Yasemin Erdogan, Shishir Nagaraja, Chuadhry Mujeeb Ahmed, Ryan Shah
AI Research AI

The Bidding Games: Reinforcement Learning for MEV Extraction on Polygon Blockchain

arXiv:2510.14642v2 Announce Type: replace-cross Abstract: In blockchain networks, the strategic ordering of transactions within blocks has emerged as a significant source of profit extraction, known as Maximal…

Source: arXiv cs.AI Andrei Seoev, Leonid Gremyachikh, Anastasiia Smirnova, Yash Madhwal, Alisa Kalacheva, Dmitry Belousov, Ilia Zubov, Aleksei Smirnov, Denis Fedyanin, Vladimir Gorgadze, Yury Yanovich
AI Research AI

Regressor-Guided Image Editing Shifts Emotion and Disengagement Timing in Social Media

arXiv:2501.12289v3 Announce Type: replace-cross Abstract: Internet overuse is a widespread phenomenon in today's digital society. Existing interventions, such as time limits or grayscaling, often rely on restrictive…

Source: arXiv cs.AI Christoph Gebhardt, Robin Willardt, Seyedmorteza Sadat, Chih-Wei Ning, Andreas Brombach, Jie Song, Otmar Hilliges, Christian Holz
AI Research AI

Causal Reasoning with Bipartite Graphical Causal Models

arXiv:2608.19831v1 Announce Type: new Abstract: Causal Bayesian networks (CBNs) and structural causal models (SCMs) are the dominant frameworks for graphical causal reasoning, but they cannot adequately represent all…

Source: arXiv cs.AI Joris M. Mooij
AI Research AI

A Distributional Robustness Margin For Pathology Foundation Models

arXiv:2607.25497v3 Announce Type: replace-cross Abstract: Pathology foundation models encode non-biological variation introduced by tissue preparation, staining and scanning, enabling shortcut learning that undermines…

Source: arXiv cs.AI Cl\'ement Grisi, Jeroen van der Laak, Geert Litjens
AI Research AI

LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures

arXiv:2608.15242v2 Announce Type: replace Abstract: When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result but not where the decisive error entered the trajectory. Developers…

Source: arXiv cs.AI Yunfei Zhang, Boyu Feng, Changhua Pei, Zexin Wang, Zhihuang Peng, Xinlong Liu, Hengyue Jiang, Difeng Ma, Jiayi Zhang, Yongzhou Yao, Yanan Zhao, Fei Sun, Yintong Huo, Zhaoyang Liu, Jingjing Li, Gaogan…
AI Research AI

GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis

arXiv:2608.09921v2 Announce Type: replace Abstract: Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from engineering domains such as power system analysis,…

Source: arXiv cs.AI Alban Puech, Matteo Mazzonelli, Tamara R. Govindasamy, Mangaliso Mngomezulu, H\'ector Maeso-Garc\'ia, Thomas Tolhurst, Javad Bayazi, Ali Moeini, Naomi Simumba, Celia Cintas, David Nelischer, Romeo Ki…
AI Research AI

Towards Quantifying Benchmark Optimization in ASR Models

arXiv:2608.19936v1 Announce Type: cross Abstract: Public benchmarks are important measures of Automatic Speech Recognition (ASR) model capabilities. However, by nature of being public, there is risk of models being…

Source: arXiv cs.AI Theo Lebryk, David Ayllon, Alice Baird, Jakub Piotr C{\l}apa, Jens Madsen, Panagiotis Tzirakis
AI Research AI

Electronic Navigational Chart Change Classification

arXiv:2608.20218v1 Announce Type: new Abstract: Electronic Navigational Charts (ENCs) are geospatial vector datasets used in maritime navigation systems that represent hydrographic and navigational information such as…

Source: arXiv cs.AI Jacob Arndt, Abhishek Potnis, Alexandre Sorokine
AI Research AI

Evidence-Gated Task and Motion Planning with Vision-Language Models

arXiv:2608.20084v1 Announce Type: cross Abstract: Robots executing long-horizon manipulation tasks from natural-language instructions must reason about both semantic task structure and geometric feasibility. However,…

Source: arXiv cs.AI Tsunehiko Tanaka, Matthew Stephenson, Alistair Macvicar, Edgar Simo-Serra
AI Research AI

Scientific Data Skills: Enabling Agent-Ready Scientific Data Services at Scale

arXiv:2608.19625v1 Announce Type: new Abstract: Scientific data are increasingly used by AI agents, yet existing dataset representations provide limited support for autonomous discovery, interpretation, and invocation.…

Source: arXiv cs.AI Xiaohan Huang, Qingqing Long, Xiaolei Du, Siyu Pu, Jiawen Xu, Haotian Chen, Chenyang Zhao, Jinbiao Liu, Xuezhi Wang, Hao Wang, Hengshu Zhu, Yuanchun Zhou
AI Research AI

VGI-BENCH: Probing Visual Intelligence in Video Generation Models

arXiv:2608.19583v1 Announce Type: cross Abstract: Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable evaluation remains…

Source: arXiv cs.AI Xuan He, Cong Wei, Yuhao Cheng, Linrui Ma, Yuxuan Zhang, Zuojun Li, Yuhao Wen, Zeyi Liu, Yuren Hao, Songcheng Cai, Keming Wu, Penghui Du, Kai Zou, Rui Yang, Chenkai Sun, Ke Yang, Ping Nie, Kelsey R A…
AI Research AI

SoftVTBench: A Safety-Aware Visuo-Tactile Benchmark for Physically Constrained Robotic Manipulation of Deformable Objects (Early Version)

arXiv:2607.04234v2 Announce Type: replace-cross Abstract: Deformable object manipulation poses challenges beyond task completion: successful execution must also maintain safe physical interaction, holding the object…

Source: arXiv cs.AI Bowen Jing, Mingxin Wang, Ruiyang Hao, Chenchen Ge, Hanwen Shen, Junjie He, Yang Cui, Yiming Hou, Weitao Zhou, Jiawei Wang, Minglei Li, Dandan Zhang, Ding Zhao, Houde Liu, Xiaofan Li, Si Liu, Ping Lu…
AI Research AI

Can Predicted Dynamics Exist in the Physical World?

arXiv:2606.00089v2 Announce Type: replace-cross Abstract: Can learned state-action proposals exist in the physical world? To filter infeasible commands before execution, policies are often wrapped in a runtime monitor.…

Source: arXiv cs.AI Barak Or
AI Research AI

TT-net: Quantum Inspired Tensor Network Denoising in Conditional GANs

arXiv:2608.19789v1 Announce Type: new Abstract: Developed as a workhorse for classical simulations of quantum algorithms and quantum many-body systems, Tensor Network methods have entered the scientific mainstream in…

Source: arXiv cs.AI Michal A. Sterzel, Marko J. Ran\v{c}i\'c
AI Research AI

Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees

arXiv:2608.19993v1 Announce Type: new Abstract: Loading reusable skill documents into a bounded context window is now the primary way large language model (LLM) agents acquire task-specific capabilities, which makes…

Source: arXiv cs.AI Yu Chen, Ruishuo Chen, Xun Wang, Zhuoran Li, Longbo Huang
AI Research AI

Fairness-Aware Network Embeddings: Methods, Applications, and Challenges

arXiv:2608.19381v1 Announce Type: cross Abstract: Network embedding methods learn low-dimensional representations of graph-structured data to support downstream tasks such as node classification, link prediction, and…

Source: arXiv cs.AI Ella Has, Harshith Kumar Yadav, Gaurav Dixit, Mykola Pechenizkiy, Akrati Saxena
AI Research AI

When AI Writes, Who Gets Cited? Evidence of Citation Monoculture Across Language Models

arXiv:2608.19230v1 Announce Type: cross Abstract: As language models move from drafting prose to running literature-search agents with tool calls, fabricated references are becoming easier to catch and constrain. The…

Source: arXiv cs.AI Sina Alemohammad, Denghui Zhang, Bolong Tang, Anthony Qin, Gengchen Mai, Ahmed Abbasi, Richard Baraniuk, Zhangyang Wang
AI Research AI

TestifAI: Tomography-Based Testing for Deep Learning Systems

arXiv:2608.18900v2 Announce Type: replace Abstract: As AI systems are increasingly deployed in safety-critical application domains (e.g., autonomous driving), associated risks increase too. Deep learning models…

Source: arXiv cs.AI Arooj Arif, Tobias Hartung, Elena Botoeva, Alexandros Koliousis
AI Research AI

Towards general embodied intelligence: integrating large language models, knowledge bases, and reasoning capabilities to build the next generation of AI agents

arXiv:2608.19794v1 Announce Type: new Abstract: The convergence of large language models (LLMs), structured knowledge bases (KBs), and reasoning ability (RA) presents a promising trajectory toward general embodied…

Source: arXiv cs.AI Fujiang Yuan, Xia Huang, Lusheng Wang, Jun Ding, Zhen Tian, Yuxin Wang, Shaojie Gu, Yuki Funabora, Yanhong Peng, Zebing Mao
AI Research AI

InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries

arXiv:2608.20220v1 Announce Type: new Abstract: Legal AI systems are increasingly used to answer legal questions, yet existing benchmarks assume queries arrive fully specified. In practice, users omit facts that…

Source: arXiv cs.AI Samuel J. Vincent, Daniel Calloway, Fangyi Yu, Andrew M. Bean, Nabeel Seedat
AI Research AI

Bringing analytic rigor to agentic AI for science: The Brain Researcher platform for neuroimaging data analysis

arXiv:2608.19902v1 Announce Type: new Abstract: AI agents can execute scientific analyses, but an analytic output becomes a defensible claim only after alternatives are weighed and the claim is limited to what the…

Source: arXiv cs.AI Zijiao Chen, Nicholas Lu, Xinhui Li, Jocelyn A. Ricard, Ce Ju, Huan H. Wang, Christian Kindermann, Jeanette A. Mumford, Steven Dillmann, James Kent, Alejandro de la Vega, Sanmi Koyejo, Vince D. Calho…
AI Research AI

Contrastive Mixed Prompt Learning for Incomplete Multimodal Sentiment Analysis with Unseen Modality Combination

arXiv:2608.20019v1 Announce Type: new Abstract: Incomplete multimodal sentiment analysis has garnered significant attention in recent years. Existing approaches typically assume that data is missing at random or are…

Source: arXiv cs.AI Kaixin Xu, NaiJin Liu, Yulin Kang, Tangyue Jin, Zixuan Yu, Wenxi Zhao, Yibei Liu, Qianle Zhang, Yangyang Wu, Mengying Zhu, Meng Xi
AI Research AI

MidTool: Mid-training Data Synthesis for Agentic Tool Use

arXiv:2608.20314v1 Announce Type: new Abstract: Mid-training is increasingly recognized as a critical stage for shaping the capabilities of large language models. Recent work has shown that targeted mid-training can…

Source: arXiv cs.AI Fengqing Jiang, Yite Wang, Boyi Liu, Zhaoyang Wang, Canwen Xu, Zhewei Yao, Radha Poovendran, Yuxiong He
AI Research AI

Anatomy Contextualized Adaptation of CT Foundation Models

arXiv:2607.27154v2 Announce Type: replace-cross Abstract: CT vision-language foundation models have demonstrated promising performance across downstream tasks, but are typically trained with whole-volume representations…

Source: arXiv cs.AI Roshan Kenia, Stephanie L McNamara, William Lotter
AI Research AI

EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models

arXiv:2608.20055v1 Announce Type: cross Abstract: Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet whether these hidden CoTs…

Source: arXiv cs.AI Yiting Qu, Ziqing Yang, Chi Cui, Ye Leng, Junjie Chu, Yang Zhang
AI Research AI

Escaping the Quicksand: A Call to Arms

arXiv:2608.19674v1 Announce Type: cross Abstract: Computing has been an astonishing success - but the accumulated technical debt exposes us all to huge costs in business and societal risk. For 75 years, we've built…

Source: arXiv cs.AI Peter Sewell, Jean Pichon-Pharabod
AI Research AI

Power Couple? AI Growth and Renewable Energy Investment

arXiv:2603.26678v3 Announce Type: replace-cross Abstract: Artificial intelligence (AI) and renewable energy are increasingly being described as a \mbox{``power couple,''} based on the idea that rapid growth in AI will…

Source: arXiv cs.AI Luyi Gui, Tinglong Dai
AI Research AI

A three-dimensional typology of agency for advanced AI systems

arXiv:2608.20041v1 Announce Type: new Abstract: Research on the agency of advanced artificial intelligence (AI) systems focuses on agency as a normative concept and on the agency of particularly agentic AI systems.…

Source: arXiv cs.AI Willem Fourie
AI Research AI

VISD: Enhancing Video Reasoning via Structured Self-Distillation

arXiv:2605.06094v5 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long,…

Source: arXiv cs.AI Hao Lin, Kunyang Lv, Xu Jiang, Jingqi Tian, Zhongjing Du, Jiayu Ding, Qiaoman Zhang, Hongbo Jin
AI Research AI

Learning Early-to-Final Solution Consistency for MILP Acceleration

arXiv:2608.19953v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) is a fundamental problem class in operations research and combinatorial optimization, with broad applications to industrial…

Source: arXiv cs.AI Guanlin Li, Chengrui Gao, Chenguang Wang, Haopu Shang, Zherong Zhang, Ke Xue, Jixiang Lu, Weiyong Yang, Chao Qian
AI Research AI

TESTNAV: Pareto-Guided Search for Compositional Robustness Testing

arXiv:2608.19882v1 Announce Type: new Abstract: Deep learning models remain vulnerable to real-world input perturbations, especially when multiple corruptions co-occur in the same input (e.g., brightness shifts and…

Source: arXiv cs.AI Arooj Arif, Tobias Hartung, Elena Botoeva, Alexandros Koliousis
AI Research AI

DA-WAM: Decision-Aligned Future Latents for Driving World Models

arXiv:2608.19085v2 Announce Type: replace-cross Abstract: Anticipating how scenes evolve under ego actions is fundamental to safe autonomous driving, yet the full potential of world models for decision-making remains…

Source: arXiv cs.AI Ruiguo Zhong, Benshan Ma, Xiaolong Chen, Lang Zhang, Mingyue Feng, Yaonong Wang, Pei Liu, Jun Ma
AI Research AI

Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networks

arXiv:2608.19817v1 Announce Type: cross Abstract: Conventional convolutional kernels are typically defined on fixed discrete grids, limiting their ability to accommodate heterogeneous local structures. Existing adaptive…

Source: arXiv cs.AI Lan Guo, Mengling Li, Haoran Li, Jun Shen, Yuanbo Jiang, Qingguo Zhou, Binbin Yong
AI Research AI

WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN

arXiv:2608.07267v2 Announce Type: replace Abstract: Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map…

Source: arXiv cs.AI Yuehao Huang, Yunzi Wu, Xiaotao Zhang, Xinhai Li, Jiankun Dong, Jiajun Lv, Chi Zhang, Chenjia Bai, Yong Liu, Xuelong Li
AI Research AI

Mapping General-Purpose AI Governance in Twenty AI Middle-Power Jurisdictions

arXiv:2608.19278v1 Announce Type: cross Abstract: The most capable general-purpose AI (GPAI) models are mostly built in two jurisdictions, the United States and China, but the risks they carry land globally. Regionally…

Source: arXiv cs.AI Josephine Schwab, Nathan Naidoo, Ferruccio Barazzutti, Sheryn Lee, Caio Vieira Machado
AI Research AI

SafeBranch: Branch-Pair Safety Alignment for Embodied Agents

arXiv:2608.19729v1 Announce Type: new Abstract: Vision-language-model-based embodied agents can complete instructed tasks but often violate safety constraints in the process, a problem recently framed as interactive…

Source: arXiv cs.AI Hyunse Lee, Jiwoo Jeong, Haneul Lee, Kyochul Jang, Youngjae Yu, Woojin Lee
AI Research AI

Extended to Reality: Prompt Injection in 3D Environments

arXiv:2602.07104v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse applications…

Source: arXiv cs.AI Zhuoheng Li, Ying Chen
AI Research AI

ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis

arXiv:2604.02022v4 Announce Type: replace Abstract: Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than…

Source: arXiv cs.AI Yu Li, Haoyu Luo, Yuejin Xie, Yuqian Fu, Zhonghao Yang, Shuai Shao, Qihan Ren, Wanying Qu, Yanwei Fu, Yujiu Yang, Jing Shao, Xia Hu, Dongrui Liu
AI Research AI

EXIMO: VLM Guided Exploration of VLA Policies

arXiv:2608.19891v1 Announce Type: new Abstract: How to efficiently finetune robot policies to learn new tasks on the fly? State of the art robotic manipulation policies are based on behaviour cloning of large…

Source: arXiv cs.AI Bhavya Sukhija, Oliver Groth, Mohit Shridhar, Tim Hertweck, Michael Bloesch, Markus Wulfmeier, Abbas Abdolmaleki, Martin Riedmiller
AI Research AI

Towards Professional Tennis Styles for Humanoid Robots with Adaptive Motion Planning and Tracking

arXiv:2608.20087v1 Announce Type: cross Abstract: Humanoid robots have recently demonstrated promising capabilities in real-world ball sports. However, achieving professional motion styles while maintaining strong task…

Source: arXiv cs.AI Tao Huang, Ruofei Liu, Xuchen Tang, Xinyin Zhang, Junli Ren, Huayi Wang, Feiyu Jia, Yukai Qi, Kangning Yin, Weishuai Zeng, Lipeng Chen, Xi Li, Ting Wu, Kailin Li, Ruoli Dai, Jingbo Wang, Lei Han, Jia…
AI Research AI

How to Navigate Uncertainty About AI Consciousness

arXiv:2608.19215v1 Announce Type: new Abstract: Given deep uncertainty about the possibility of artificial consciousness, it is unclear how we should treat potentially sentient AI. On the one hand, we could assume…

Source: arXiv cs.AI Dr Tom McClelland
AI Research AI

Repo0: Design-Driven Zero-to-All Code Generation

arXiv:2608.19854v1 Announce Type: cross Abstract: Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption…

Source: arXiv cs.AI Silin Chen, Haoyi Teng, Xiaodong Gu, Yuling Shi, Jiale Huang, Yongpan Wang, Hongyu Zhang, Haibing Guan
AI Research AI

Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation

arXiv:2608.20316v1 Announce Type: new Abstract: Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the…

Source: arXiv cs.AI Adam Fisch, Shubhendu Trivedi, Fantine Huot, William W. Cohen, Michael Kaisers, Mirella Lapata, Kate Larson, Jacob Eisenstein
AI Research AI

Computational Phenomenology of Borderline Personality Disorder: A Comparative Evaluation of LLM-Simulated Expert Personas and Human Clinical Experts

arXiv:2508.19008v3 Announce Type: replace Abstract: Building on a human-led thematic analysis of clinical life-story interviews (> 150,000 words) with inpatients with Borderline Personality Disorder, this study examines…

Source: arXiv cs.AI Marcin Moskalewicz, Anna Sterna, Karolina Dro\.zd\.z, Kacper Dudzic, Marek Pokropski, Paula Flores
AI Research AI

DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation

arXiv:2608.20114v1 Announce Type: new Abstract: Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future observations and control. Existing world-action models, developed…

Source: arXiv cs.AI Siyuan Ma, Boshi Zhang, Yutian Zhang, Qinglian Wu, Jiaqi Zhai, Dong Wei, Qiaojun Yu
AI Research AI

CharTool: Tool-Integrated Visual Reasoning for Chart Understanding

arXiv:2604.02794v2 Announce Type: replace Abstract: Charts are ubiquitous in scientific and financial literature for presenting structured data. However, chart reasoning remains challenging for multimodal large language…

Source: arXiv cs.AI Situo Zhang, Yifan Zhang, Zichen Zhu, Da Ma, Lei Pan, Danyang Zhang, Zihan Zhao, Lu Chen, Kai Yu
AI Research AI

Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models

arXiv:2608.19556v1 Announce Type: cross Abstract: Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the…

Source: arXiv cs.AI Yuanhao Ban, Jiaqi Feng, Hengguang Zhou, Xiaohuan Pei, Justin Cui, Cho-Jui Hsieh
AI Research AI

Gen AI in Proof-based Math Courses: A Pilot Study

arXiv:2509.13570v2 Announce Type: replace Abstract: With the rapid rise of generative AI in higher education, understanding how students use AI is increasingly important. This exploratory study examines student use and…

Source: arXiv cs.AI Hannah Klawa, Shraddha Rajpal, Cigole Thomas
AI Research AI

Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models

arXiv:2608.20237v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) combine linguistic reasoning with visual perception, yet their ability to perform visual spatial planning under explicit or…

Source: arXiv cs.AI Yu Chen, Ting Lei, Yaoyi Li, Jia Cai, Zhecen Wu, Yang Liu
AI Research AI

FMT$^{\mathrm{X}}$: Lazy Wavefront Search for Dynamic Replanning

arXiv:2509.08521v2 Announce Type: replace-cross Abstract: FMT$^{*}$ plans efficiently in static worlds by expanding a cost-ordered wavefront and collision-checking lazily, but its single-pass unvisited rule cannot…

Source: arXiv cs.AI Soheil Espahbodi Nia
AI Research AI

Interaction valence reveals contrasting social networks in dairy cattle

arXiv:2608.19222v1 Announce Type: new Abstract: Social relationships shape access to resources, exposure to conflict and group stability, yet automated livestock monitoring typically treats behaviour as isolated events.…

Source: arXiv cs.AI Sibi Parivendan, Suresh Raja Neethirajan
AI Research AI

ReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance

arXiv:2608.19974v1 Announce Type: new Abstract: LLM agents in financial markets may cite rules yet still submit orders that violate executable constraints or misread surveillance evidence. We introduce ReguSim, a…

Source: arXiv cs.AI Yiyang Luo, Yihang Jiang, Qijun Xie, Liang Lan, Lin Willian Cong, Anyi Rao, Yunya Song