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)

20,101 to 20,160 of 27,659

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
Songqiao Su, Xiaoya Li, Albert Wang +3
cs.LGcs.AIarXiv:2512.02551v42025
Revisiting Pre-trained Language Models for Vulnerability Detection
Youpeng Li, Weiliang Qi, Xuyu Wang +2
cs.CRcs.AIcs.LGarXiv:2507.16887v22025
Common 7B Language Models Already Possess Strong Math Capabilities
Chen Li, Weiqi Wang, Jingcheng Hu +5
cs.CLcs.AIarXiv:2403.04706v12024
Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values
Yejin Bang, Tiezheng Yu, Andrea Madotto +3
cs.CLcs.AIarXiv:2210.07652v12022
Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models
Teng Wang, Zhangyi Jiang, Zhenqi He +9
cs.CLcs.AIarXiv:2503.13551v52025
ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation
Zihan Yang, Shuyuan Tu, Licheng Zhang +3
cs.CVcs.AIarXiv:2602.09014v12026
Contrastive Learning for Fair Representations
Aili Shen, Xudong Han, Trevor Cohn +2
cs.CLcs.AIarXiv:2109.10645v12021
Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs
Yukun Jiang, Hai Huang, Mingjie Li +3
cs.LGcs.AIcs.CRarXiv:2602.08621v12026
Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI
Kairos Team, Fei Wang, Shan You +21
cs.AIcs.CVarXiv:2606.16533v32026
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives
Amit Dhurandhar, Pin-Yu Chen, Ronny Luss +4
cs.AIcs.CVcs.LGarXiv:1802.07623v22018
When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
Scott Emmons, Erik Jenner, David K. Elson +5
cs.AIcs.CLarXiv:2507.05246v12025
Students' Voices on Generative AI: Perceptions, Benefits, and Challenges in Higher Education
Cecilia Ka Yuk Chan, Wenjie Hu
cs.CYcs.AIarXiv:2305.00290v12023
Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents
Sicheng Xie, Yitong Chen, Haidong Cao +3
cs.ROcs.AIarXiv:2609.37810v12026
Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples
Chumeng Liang, Xiaoyu Wu, Yang Hua +6
cs.CVcs.AIcs.CRarXiv:2302.04578v22023
SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned
Cen Zhang, Younggi Park, Fabian Fleischer +18
cs.CRcs.AIarXiv:2602.07666v52026
When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory
Kazuki Nakayashiki
cs.IRcs.AIcs.CLarXiv:2608.25553v12026
GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets
Gaspard Botté, Séverin Baroudi, Samir Sadok +5
eess.AScs.AIcs.LGarXiv:2609.37798v12026
Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning
Da Yin, Liunian Harold Li, Ziniu Hu +2
cs.CLcs.AIcs.CVarXiv:2109.06860v12021
Spatial-temporal Concept based Explanation of 3D ConvNets
Ying Ji, Yu Wang, Kensaku Mori +1
cs.CVcs.AIarXiv:2206.05275v12022
Learning to Reason under Off-Policy Guidance
Jianhao Yan, Yafu Li, Zican Hu +5
cs.LGcs.AIcs.CLarXiv:2504.14945v52025
A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses
Zhangshu Joshua Jiang, Zina Ibrahim, James T. Teo
cs.CLcs.AIarXiv:2609.37788v12026
Large-Scale Evolution of Image Classifiers
Esteban Real, Sherry Moore, Andrew Selle +5
cs.NEcs.AIcs.CVarXiv:1703.01041v22017
MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning
Xiaoyu Tao, Mingyue Cheng, Ze Guo +4
cs.LGcs.AIarXiv:2602.03164v22026
Multi-Agent Orchestration of 3GPP Channel Estimators
I. Zakir Ahmed, Hamid Sadjadpour
cs.ITcs.AIeess.SParXiv:2609.29044v12026
Recommendations as Treatments: Debiasing Learning and Evaluation
Tobias Schnabel, Adith Swaminathan, Ashudeep Singh +2
cs.LGcs.AIcs.IRarXiv:1602.05352v22016
6G White Paper on Edge Intelligence
Ella Peltonen, Mehdi Bennis, Michele Capobianco +16
cs.DCcs.AIcs.NIarXiv:2004.14850v12020
CoQA: A Conversational Question Answering Challenge
Siva Reddy, Danqi Chen, Christopher D. Manning
cs.CLcs.AIcs.LGarXiv:1808.07042v22018
Computational Aspects of Multi-Winner Approval Voting
Haris Aziz, Serge Gaspers, Joachim Gudmundsson +3
cs.GTcs.AIcs.MAarXiv:1407.3247v12014
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Rui Yang, Qianhui Wu, Yuxi Chen +7
cs.LGcs.AIcs.CLarXiv:2606.02031v22026
Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance
Abdelghny Orogat, Ana Rostam, Essam Mansour
cs.AIarXiv:2602.03128v22026
RAPTOR: Ridge-Adaptive Logistic Probes
Ziqi Gao, Yaotian Zhu, Qingcheng Zeng +4
cs.LGcs.AIarXiv:2602.00158v22026
Mitigating Language-Dependent Ethnic Bias in BERT
Jaimeen Ahn, Alice Oh
cs.CLcs.AIarXiv:2109.05704v22021
Agent Exchange: Shaping the Future of AI Agent Economics
Yingxuan Yang, Ying Wen, Jun Wang +1
cs.AIcs.MAarXiv:2507.03904v12025
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
Gongfan Fang, Hongxu Yin, Saurav Muralidharan +5
cs.AIcs.CLcs.LGarXiv:2409.17481v22024
Prompt Engineering a Prompt Engineer
Qinyuan Ye, Maxamed Axmed, Reid Pryzant +1
cs.CLcs.AIcs.LGarXiv:2311.05661v32023
VIF-Bench: Evaluating Visual Instruction Following in Multi-Reference Image Generation
Yuta Oshima, Masakazu Yoshimura, Masahiro Suzuki +2
cs.CVcs.AIarXiv:2609.37709v12026
Dual Latent Memory for Visual Multi-agent System
Xinlei Yu, Chengming Xu, Zhangquan Chen +8
cs.AIcs.CVarXiv:2602.00471v22026
Atria Dawn: The Dawn of Agentic Superintelligence
Honglin Guo, Tao Gui, Yicheng Chen +140
cs.AIarXiv:2609.15818v12026
DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars
Yuchi Tian, Kexin Pei, Suman Jana +1
cs.SEcs.AIcs.LGarXiv:1708.08559v22017
The Impact of LLM-Assistants on Software Developer Productivity: A Systematic Review and Mapping Study
Amr Mohamed, Maram Assi, Mariam Guizani
cs.SEcs.AIcs.HCarXiv:2507.03156v32025
Goodput Maximization for Large Language Model Edge Inference: A Two-Phase Maskable PPO Approach
Xiaojing Chen, Qi Zhang, Wei Ni +2
eess.SYcs.AIarXiv:2608.25543v12026
Responsible Evaluation of AI for Mental Health
Hiba Arnaout, Anmol Goel, H. Andrew Schwartz +13
cs.CYcs.AIarXiv:2602.00065v22026
Acting Less is Reasoning More! Teaching Model to Act Efficiently
Hongru Wang, Cheng Qian, Wanjun Zhong +7
cs.AIcs.CLarXiv:2504.14870v22025
Bilateral Multi-Perspective Matching for Natural Language Sentences
Zhiguo Wang, Wael Hamza, Radu Florian
cs.AIcs.CLarXiv:1702.03814v32017
When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task
Sai Sumedh R. Hindupur, Hadas Orgad, Thomas Fel +1
cs.LGcs.AIcs.CLarXiv:2609.37680v12026
EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning
Yufei He, Juncheng Liu, Zhiyuan Hu +9
cs.AIarXiv:2601.22964v12026
Large Language Model Enhanced Multi-Agent Systems for 6G Communications
Feibo Jiang, Li Dong, Yubo Peng +5
cs.AIarXiv:2312.07850v12023
Orchestrating Specialized Agents for Trustworthy Enterprise RAG
Xincheng You, Qi Sun, Neha Bora +4
cs.IRcs.AIarXiv:2601.18267v12026
LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion
Guanghao Zhou, Panjia Qiu, Cen Chen +4
cs.CYcs.AIarXiv:2602.00038v12026
Value Iteration Networks
Aviv Tamar, Yi Wu, Garrett Thomas +2
cs.AIcs.LGcs.NEarXiv:1602.02867v42016
Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment
Tiejin Chen, Xiaoou Liu, Vishnu Nandam +2
cs.LGcs.AIarXiv:2601.17329v12026
Making Large Language Models Better Reasoners with Step-Aware Verifier
Yifei Li, Zeqi Lin, Shizhuo Zhang +4
cs.CLcs.AIarXiv:2206.02336v32022
Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis
Yuxuan Ou, Konstantinos Kamnitsas, OxAAA Study +3
cs.CVcs.AIarXiv:2610.03224v12026
Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs
Myra Cheng, Robert D. Hawkins, Dan Jurafsky
cs.CLcs.AIcs.CYarXiv:2601.04435v12026
Temporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast Trajectories
Emanuele Albini, Francesca Toni, Saumitra Mishra +1
cs.LGcs.AIarXiv:2610.09994v12026
T-REX: Mixture-of-Rank-One-Experts with Semantic-aware Intuition for Multi-task Large Language Model Finetuning
Rongyu Zhang, Yijiang Liu, Huanrui Yang +5
cs.LGcs.AIarXiv:2404.08985v22024
Learning to Act Robustly with View-Invariant Latent Actions
Youngjoon Jeong, Junha Chun, Taesup Kim
cs.ROcs.AIcs.LGarXiv:2601.02994v12026
Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning
Daniel Guo, Bernardo Avila Pires, Bilal Piot +4
cs.LGcs.AIarXiv:2004.14646v12020
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
Guocheng Qian, Yuchen Li, Houwen Peng +4
cs.CVcs.AIarXiv:2206.04670v22022
UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures
Homa Esfahanizadeh, Matin Mortaheb, Jinfeng Du +1
cs.LGcs.AIcs.ITarXiv:2608.16696v12026

Artificial Intelligence

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

Revisiting Pre-trained Language Models for Vulnerability Detection

Common 7B Language Models Already Possess Strong Math Capabilities

Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values

Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models

ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation

Contrastive Learning for Fair Representations

Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs

Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI

Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives

When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors

Students' Voices on Generative AI: Perceptions, Benefits, and Challenges in Higher Education

Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents

Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples

SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned

When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory

GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets

Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning

Spatial-temporal Concept based Explanation of 3D ConvNets

Learning to Reason under Off-Policy Guidance

A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses

Large-Scale Evolution of Image Classifiers

MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning

Multi-Agent Orchestration of 3GPP Channel Estimators

Recommendations as Treatments: Debiasing Learning and Evaluation

6G White Paper on Edge Intelligence

CoQA: A Conversational Question Answering Challenge

Computational Aspects of Multi-Winner Approval Voting

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance

RAPTOR: Ridge-Adaptive Logistic Probes

Mitigating Language-Dependent Ethnic Bias in BERT

Agent Exchange: Shaping the Future of AI Agent Economics

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models

Prompt Engineering a Prompt Engineer

VIF-Bench: Evaluating Visual Instruction Following in Multi-Reference Image Generation

Dual Latent Memory for Visual Multi-agent System

Atria Dawn: The Dawn of Agentic Superintelligence

DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars

The Impact of LLM-Assistants on Software Developer Productivity: A Systematic Review and Mapping Study

Goodput Maximization for Large Language Model Edge Inference: A Two-Phase Maskable PPO Approach

Responsible Evaluation of AI for Mental Health

Acting Less is Reasoning More! Teaching Model to Act Efficiently

Bilateral Multi-Perspective Matching for Natural Language Sentences

When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task

EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning

Large Language Model Enhanced Multi-Agent Systems for 6G Communications

Orchestrating Specialized Agents for Trustworthy Enterprise RAG

LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion

Value Iteration Networks

Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment

Making Large Language Models Better Reasoners with Step-Aware Verifier

Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis

Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs

Temporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast Trajectories

T-REX: Mixture-of-Rank-One-Experts with Semantic-aware Intuition for Multi-task Large Language Model Finetuning

Learning to Act Robustly with View-Invariant Latent Actions

Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures