Artificial Intelligence

Papers filed under cs.AI on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

14,521 to 14,580 of 15,271

EgoGazeLite: On-Device Egocentric Gaze Prediction for Token-Efficient Multimodal LLM Video Input
Matteo Stoiber, Niels Buus Lassen
cs.CVcs.AIarXiv:2608.15614v12026
Invariant Pretraining for Robust Code Representations
Yifeng He, Yundi Xu, Christopher Castro Gaw Gonzalo +2
cs.LGcs.AIcs.SEarXiv:2608.15412v12026
Does the Proof Prove It That Way? Faithful Formalization of Elements Proofs
Tadd Mao, Tianjun Zhong, Dhruva Arekar +5
cs.AIarXiv:2608.15432v12026
AutoSR: Automatic Symbolic Regression by Searching Research States
Kejia Zhang, Youran Sun, Xinyu Ren +2
cs.SCcs.AIcs.LGarXiv:2608.16876v12026
TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents
Huan Zhang, Mingju Chen, Dongxu Zhou +5
cs.AIarXiv:2608.16156v12026
HaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents
Shen Liu, Zhenguo Xu, Shaopu Wang +2
cs.AIcs.ROarXiv:2608.16447v12026
FeatureHospital: A Skill-Driven Multi-Agent Framework for Automated Algorithm Customization in Multi-View Multi-Label Feature Selection
Junxuan Li, Zhiqi Chen, Yuzhou Liu +2
cs.AIarXiv:2608.16148v12026
Grounding Healthcare LLMs in a Causal Knowledge Graph: Framework, Metrics, and a Cardiovascular Pilot
Ummara Mumtaz, Aimen Noor, Awais Ahmed
cs.AIcs.CLcs.IRarXiv:2608.15382v12026
SCOPE: Score-Isolated Agentic Optimization for Video World Models
Yuhua Jiang, Jiaming Wang, Qingbin Liu +1
cs.AIarXiv:2608.15043v12026
Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation
Cedar Site Bai, Duanshun Li, Zhenyu Liao +6
cs.IRcs.AIcs.CLarXiv:2608.15949v12026
FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction
Ali Boudaghi, Alireza Nemati, Hadi Zare
cs.LGcs.AIstat.MLarXiv:2608.15727v12026
Hierarchical Adaptive Feature Refinement Network for VHR Remote Sensing Image Segmentation
Shuaishuai Cao, Meng Tang, Shuwei Peng +7
cs.CVcs.AIarXiv:2608.15647v12026
Bias-Corrected Ceilings of Emotion Predictability from Human Label Variation Based on Instance-Level Fano Bounds
Keito Inoshita
cs.AIarXiv:2608.15619v12026
GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation
Zhiqiang Hu, Shouren Huang, Masatoshi Ishikawa
cs.ROcs.AIarXiv:2608.14986v12026
When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation
Wenhao Yuan, Chenchen Lin, Wenhao Hu +4
cs.DCcs.AIcs.LGarXiv:2608.15639v12026
Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation
Rui Wang, Jiazhou Wang, Zheng Wei +16
cs.AIarXiv:2608.15877v12026
Mental Model Management: An Operator-Based Framework for LLM Memory
Oliver Kramer
cs.AIcs.NEarXiv:2608.15451v12026
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
Heming Zou, Qi Wang, Yun Qu +9
cs.LGcs.AIcs.CLarXiv:2606.11119v12026
Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
Yujun Wu, Dongxu Zhang, Xinchen Li +11
cs.AIarXiv:2604.28158v22026
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
Ye Yuan, Rui Song, Weien Li +12
cs.CLcs.AIcs.MAarXiv:2605.27068v12026
Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
Seongheon Park, Wendi Li, Changdae Oh +4
cs.ROcs.AIarXiv:2605.30834v12026
NumerosityVLM: A Cognitively Inspired Benchmark for Interpreting Numerosity Representations in Vision-Language Models
Yiming Fu, Fangjun Li, Xiujin Liu +7
cs.CVcs.AIarXiv:2608.15425v12026
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
Fangtai Wu, Hailong Guo, Shijie Huang +7
cs.CVcs.AIarXiv:2605.25378v22026
Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments
Yuxin Chen, Xiaodong Cai, Junfeng Fang +9
cs.AIarXiv:2605.27209v12026
TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity
Armin Steinhauser
cs.LGcs.AIarXiv:2608.15767v12026
When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations
Yuqi Chen, Sixuan Li, Yunfeng Cai +3
cs.CLcs.AIarXiv:2608.15654v12026
Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration
Yiqi Liu, Yang Wang, Songxin Wang +2
cs.AIarXiv:2608.15772v12026
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
Haoming Xu, Weihong Xu, Zongrui Li +6
cs.AIcs.CLcs.LGarXiv:2605.30219v12026
Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation
Zixuan Jiang, Yanqiao Zhu, Peng Wang +8
cs.AIcs.CLarXiv:2605.29430v12026
MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding
Qian Kou, Xiaofeng Shi, Yulin Li +4
cs.CVcs.AIarXiv:2605.30794v22026
AdaCodec: A Predictive Visual Code for Video MLLMs
Haowen Hou, Zhen Huang, Zheming Liang +8
cs.CVcs.AIcs.CLarXiv:2606.02569v12026
EA-LiteUNet: An Edge-Adaptive and Resource-Efficient U-Net for Boundary-Sensitive Dermoscopic Image Segmentation
Wang Jiangtao, Nur Intan Raihana Ruhaiyem, Fu Panpan +2
cs.CVcs.AIarXiv:2608.15537v12026
ARENA: Automated Red-Teaming for Large Audio Language Models
Jiaming He, Zhicong Huang, Tian Jin +5
cs.SDcs.AIarXiv:2608.15578v12026
Feasible and Novel Synthetic Population Generation with Tabular and Sequential Travel Attributes
Farbod Abbasi, Zachary Patterson, Bilal Farooq
cs.LGcs.AIarXiv:2608.15867v12026
EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints
Ao Zhou, Bo Dai, Le Yu +5
cs.AIcs.ROarXiv:2608.15502v12026
Agent Lightning v1.0: Towards Harnessed Agentic RL
Zhiyuan He, Siwei Zhang, Zhiwen Zhou +7
cs.AIcs.SEarXiv:2608.17528v12026
Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders
Georgii Aparin, Vadim Popov, Tasnima Sadekova +1
cs.SDcs.AIarXiv:2606.07473v12026
ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models
Rui Xu, Jiepeng Wang, Hao Pan +6
cs.LGcs.AIcs.CVarXiv:2405.13729v32024
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
Xuekang Wang, Zhuoyuan Hao, Shuo Hou +3
cs.LGcs.AIcs.CLarXiv:2606.04923v22026
Decomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and Decay
Di Bai, Feng Han, Zhenwei Tang +3
cs.IRcs.AIarXiv:2608.15780v12026
Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer
Ivan Mikheev, Viacheslav Vasilev, Anna Dmitrienko +4
cs.SDcs.AIcs.LGarXiv:2608.15690v12026
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Liliana Hotsko, Yinxi Li, Yuntian Deng +1
cs.SEcs.AIcs.CLarXiv:2606.06492v12026
Who Leads Now? Token-Level Modality Arbitration for Chart-to-Code Generation
Qinghao Fu, Yarong Wang, Shunlei Ning +6
cs.AIarXiv:2608.15510v12026
ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs
Ashutosh Hathidara, Sai Shruthi Sistla, Sebastian Schreiber +1
cs.AIcs.IRcs.LGarXiv:2606.12451v12026
Watch, Remember, Reason: Human-View Video Understanding with MLLMs
Jiahao Meng, Yue Tan, Qi Xu +12
cs.CVcs.AIcs.MMarXiv:2606.07433v12026
CEO-Bench: Can Agents Play the Long Game?
Haozhe Chen, Karthik Narasimhan, Zhuang Liu
cs.AIcs.CLcs.SEarXiv:2606.18543v22026
Playful Agentic Robot Learning
Junyi Zhang, Jiaxin Ge, Hanjun Yoo +17
cs.ROcs.AIarXiv:2606.19419v12026
Meta-CoT: Enhancing Granularity and Generalization in Image Editing
Shiyi Zhang, Yiji Cheng, Tiankai Hang +8
cs.CVcs.AIcs.LGarXiv:2604.24625v12026
Synthetic Data Augmentation for Satellite-Based Analysis of Battle-Damaged Agricultural Fields in Ukraine
Marta Sumyk, Oleksandr Kosovan, Iryna Voitsitska
cs.CVcs.AIarXiv:2608.16380v12026
Integrating Persuasion Theory into the Epidemiological Modelling of Health Misinformation Spread on Social Media
Mkululi Sikosana, Sean Maudsley-Barton, Oluwaseun Ajao
cs.SIcs.AIcs.CLarXiv:2608.15689v12026
VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience
Jianming Chen, Xuanbin Ye, Yawen Wang +3
cs.MAcs.AIarXiv:2608.16544v12026
Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors
Iyad Assaad Nekka, Hamida Seba, Walid Khaled Hidouci +1
cs.LGcs.AIarXiv:2608.15559v12026
GoalEvolve: From Handcrafted Algorithm Priors to Goal-Driven Evolution of Physical Design Algorithms
Haixu Liu, Lei Zhou, Yuhao Ren +2
cs.ARcs.AIarXiv:2608.16733v12026
Understanding and Stabilizing Deep Q-Learning via Controlled Bootstrapping and Regulated Value Dynamics
Bozhou Chen, Yongyi Wang, Hanyu Liu +2
cs.LGcs.AIarXiv:2608.16182v12026
PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning
Veit Laule, Jiangtao Shuai, Manfred Hauswirth +1
cs.AIarXiv:2608.16637v12026
Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate
Yusuke Takahashi, Kyle Wild, Asako Uraki
cs.AIcs.DBcs.IRarXiv:2608.16621v12026
Protein Structure Prediction: From Evolutionary Constraints to Generative Modeling
Wengan He, Yongsheng Luo, Lihong Jiang +2
cs.AIcs.LGarXiv:2608.16094v12026
Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation
Yijie Xu, Haopeng Jin, Run Zhou +8
cs.ROcs.AIarXiv:2608.15680v12026
Unified Pedestrian Path Prediction Using Inverse Reinforcement Learning
Šimon Sukup, Ariyan Bighashdel, Pavol Jancura
cs.AIarXiv:2608.15929v12026
A Network-driven Framework for Public Event Forecasting via Dynamic Interaction Network Evolution
Jie Wei, Yue Liu, Xiaochuan Tang +3
cs.AIarXiv:2608.15488v12026

Artificial Intelligence

EgoGazeLite: On-Device Egocentric Gaze Prediction for Token-Efficient Multimodal LLM Video Input

Invariant Pretraining for Robust Code Representations

Does the Proof Prove It That Way? Faithful Formalization of Elements Proofs

AutoSR: Automatic Symbolic Regression by Searching Research States

TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents

HaReCAP: Habitual-action Grounding for Recursive Large Language Model Agents

FeatureHospital: A Skill-Driven Multi-Agent Framework for Automated Algorithm Customization in Multi-View Multi-Label Feature Selection

Grounding Healthcare LLMs in a Causal Knowledge Graph: Framework, Metrics, and a Cardiovascular Pilot

SCOPE: Score-Isolated Agentic Optimization for Video World Models

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

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

Hierarchical Adaptive Feature Refinement Network for VHR Remote Sensing Image Segmentation

Bias-Corrected Ceilings of Emotion Predictability from Human Label Variation Based on Instance-Level Fano Bounds

GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation

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

Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation

Mental Model Management: An Operator-Based Framework for LLM Memory

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring

NumerosityVLM: A Cognitively Inspired Benchmark for Interpreting Numerosity Representations in Vision-Language Models

CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation

Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments

TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity

When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations

Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration

When Should Models Change Their Minds? Contextual Belief Management in Large Language Models

Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation

MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding

AdaCodec: A Predictive Visual Code for Video MLLMs

EA-LiteUNet: An Edge-Adaptive and Resource-Efficient U-Net for Boundary-Sensitive Dermoscopic Image Segmentation

ARENA: Automated Red-Teaming for Large Audio Language Models

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

EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints

Agent Lightning v1.0: Towards Harnessed Agentic RL

Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders

ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models

Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

Decomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and Decay

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

Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution

Who Leads Now? Token-Level Modality Arbitration for Chart-to-Code Generation

ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs

Watch, Remember, Reason: Human-View Video Understanding with MLLMs

CEO-Bench: Can Agents Play the Long Game?

Playful Agentic Robot Learning

Meta-CoT: Enhancing Granularity and Generalization in Image Editing

Synthetic Data Augmentation for Satellite-Based Analysis of Battle-Damaged Agricultural Fields in Ukraine

Integrating Persuasion Theory into the Epidemiological Modelling of Health Misinformation Spread on Social Media

VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience

Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors

GoalEvolve: From Handcrafted Algorithm Priors to Goal-Driven Evolution of Physical Design Algorithms

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

PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning

Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate

Protein Structure Prediction: From Evolutionary Constraints to Generative Modeling

Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation

Unified Pedestrian Path Prediction Using Inverse Reinforcement Learning

A Network-driven Framework for Public Event Forecasting via Dynamic Interaction Network Evolution