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)

21,841 to 21,900 of 27,211

The Alignment Problem from a Deep Learning Perspective
Richard Ngo, Lawrence Chan, Sören Mindermann
cs.AIcs.LGarXiv:2209.00626v82022
Mathematical exploration and discovery at scale
Bogdan Georgiev, Javier Gómez-Serrano, Terence Tao +1
cs.NEcs.AImath.CAarXiv:2511.02864v32025
An improvement of the convergence proof of the ADAM-Optimizer
Sebastian Bock, Josef Goppold, Martin Weiß
cs.LGcs.AIstat.MLarXiv:1804.10587v12018
Guided scenarios with simulated expert personae: a remarkable strategy to perform cognitive work
David Van Buren
cs.HCcs.AIquant-pharXiv:2306.03104v12023
BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
Bowen Wen, Kostas Bekris
cs.CVcs.AIcs.GRarXiv:2108.00516v12021
Adaptive Code Generation for Controlling Robots
Justus Flerlage, Thorsten Wittkopp, Alexander Acker +1
cs.ROcs.AIarXiv:2610.09588v12026
Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval
Jiaxi Li, Ke Deng, Yun Wang +5
cs.AIarXiv:2606.04391v12026
Factuality Challenges in the Era of Large Language Models
Isabelle Augenstein, Timothy Baldwin, Meeyoung Cha +15
cs.CLcs.AIcs.LGarXiv:2310.05189v22023
HARBOR: Automated Harness Optimization
Biswa Sengupta, Jinhua Wang
cs.LGcs.AIarXiv:2604.20938v12026
SciFact-Open: Towards open-domain scientific claim verification
David Wadden, Kyle Lo, Bailey Kuehl +4
cs.CLcs.AIarXiv:2210.13777v12022
Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation
Han Guo, Ramakanth Pasunuru, Mohit Bansal
cs.CLcs.AIcs.LGarXiv:1805.11004v12018
Diffsound: Discrete Diffusion Model for Text-to-sound Generation
Dongchao Yang, Jianwei Yu, Helin Wang +4
cs.SDcs.AIeess.ASarXiv:2207.09983v22022
Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models
Xiaomei Zhang, Zhaoxi Zhang, Leo Yu Zhang +3
cs.CRcs.AIarXiv:2601.12042v12026
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
Ke Wang, Houxing Ren, Aojun Zhou +7
cs.CLcs.AIcs.CVarXiv:2310.03731v12023
Federated Learning with Label Distribution Skew via Logits Calibration
Jie Zhang, Zhiqi Li, Bo Li +4
cs.LGcs.AIarXiv:2209.00189v22022
Query-Dependent Video Representation for Moment Retrieval and Highlight Detection
WonJun Moon, Sangeek Hyun, SangUk Park +2
cs.CVcs.AIarXiv:2303.13874v12023
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
Haonan Dong, Qiguan Feng, Kehan Jiang +3
cs.AIarXiv:2605.10365v12026
CoVer: Conflict-Aware Claim Verification
Shuning Zhang, Dai Shi, Bohao Chu +7
cs.AIarXiv:2609.00508v12026
How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies
Vincent François-Lavet, Raphael Fonteneau, Damien Ernst
cs.LGcs.AIarXiv:1512.02011v22015
Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework
Shu Zhang, Ran Xu, Caiming Xiong +1
cs.CVcs.AIcs.LGarXiv:2204.13207v12022
CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment
Chengxiao Wang, Enyi Jiang, Xiaojing Liao +1
cs.AIarXiv:2608.21278v12026
Threats, Attacks, and Defenses in Machine Unlearning: A Survey
Ziyao Liu, Huanyi Ye, Chen Chen +2
cs.CRcs.AIarXiv:2403.13682v52024
Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
Jianing Yang, Alexander Sax, Kevin J. Liang +6
cs.CVcs.AIcs.GRarXiv:2501.13928v22025
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Zixiang Chen, Yihe Deng, Huizhuo Yuan +2
cs.LGcs.AIcs.CLarXiv:2401.01335v32024
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data
Jiwen Liu, Shujuan Li, Zhixue Fang +8
cs.CVcs.AIarXiv:2606.13432v12026
Repo2Skill-Evo: Repository Skills Go Stale in Silence
Chenyuan Duan, Ge Shi, Zineng Mao +10
cs.AIcs.SEarXiv:2608.21964v12026
CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
Qixiu Li, Yaobo Liang, Zeyu Wang +15
cs.ROcs.AIcs.CLarXiv:2411.19650v12024
RLIF: Interactive Imitation Learning as Reinforcement Learning
Jianlan Luo, Perry Dong, Yuexiang Zhai +2
cs.AIcs.ROarXiv:2311.12996v22023
What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis
Xirui Li, Ming Li, Tianyi Zhou
cs.CVcs.AIarXiv:2602.12395v12026
V-STaR: Training Verifiers for Self-Taught Reasoners
Arian Hosseini, Xingdi Yuan, Nikolay Malkin +3
cs.LGcs.AIcs.CLarXiv:2402.06457v22024
Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks
Tianze Xu, Yanzhao Zheng, Pengrui Lu +11
cs.CLcs.AIarXiv:2604.02795v12026
People construct simplified mental representations to plan
Mark K. Ho, David Abel, Carlos G. Correa +3
cs.AIarXiv:2105.06948v22021
Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning
Pan Lu, Ran Gong, Shibiao Jiang +4
cs.CLcs.AIcs.CVarXiv:2105.04165v32021
Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning
Abhishek Gupta, Coline Devin, YuXuan Liu +2
cs.AIcs.ROarXiv:1703.02949v12017
Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback
Mengkang Hu, Bowei Xia, Yuran Wu +9
cs.AIcs.CLarXiv:2512.22336v12025
Stop Comparing LLM Agents Without Disclosing the Harness
Yunbei Zhang, Janet Wang, Yingqiang Ge +3
cs.AIcs.SEarXiv:2605.23950v12026
Writing for the Reviewer: Defensive Writing in GPT Models
Junchi Liao
cs.AIarXiv:2610.11355v12026
Reinforcement Learning: A Survey
L. P. Kaelbling, M. L. Littman, A. W. Moore
cs.AIarXiv:cs/9605103v11996
Learning to Watermark LLM-generated Text via Reinforcement Learning
Xiaojun Xu, Yuanshun Yao, Yang Liu
cs.LGcs.AIcs.CRarXiv:2403.10553v12024
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Kenneth Li, Aspen K. Hopkins, David Bau +3
cs.LGcs.AIcs.CLarXiv:2210.13382v52022
Value-Decomposition Networks For Cooperative Multi-Agent Learning
Peter Sunehag, Guy Lever, Audrunas Gruslys +8
cs.AIarXiv:1706.05296v12017
Frontier Learning: Training LLM Reasoners at the Edge of Capability
Robin Faro, Shyam Sundhar Ramesh, Ilija Bogunovic +1
cs.LGcs.AIcs.CLarXiv:2609.35426v12026
On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited
Xue Yang, Junchi Yan
cs.CVcs.AIarXiv:2003.05597v42020
Removing RLHF Protections in GPT-4 via Fine-Tuning
Qiusi Zhan, Richard Fang, Rohan Bindu +3
cs.CLcs.AIarXiv:2311.05553v32023
ASTAR: Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora
Xinfeng Zhang, Mingxuan Liu, Yifei Chen +9
cs.CLcs.AIarXiv:2608.20369v12026
LLM-Driven Algorithm Design for Quantum Circuit Synthesis based on Binary Decision Diagrams
Yoonju Sim, Federico Berto, Chuanbo Hua +2
cs.AIcs.ARarXiv:2609.05327v12026
TessIndex: Capability Verified Identity System for the Agent Economy
Mehul Goenka, Tejas Pathak, Siddharth Asthana
cs.AIcs.CRcs.MAarXiv:2608.21942v12026
One-Shot Generalization in Deep Generative Models
Danilo Jimenez Rezende, Shakir Mohamed, Ivo Danihelka +2
stat.MLcs.AIcs.LGarXiv:1603.05106v22016
ResidualAuth: What Authorization State Must Language Agents Preserve under Revocable Delegation?
Moonwon Choi, Seokho Jeong, Seunggeun Lee
cs.AIcs.CRarXiv:2609.08062v12026
PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
Mihir Parmar, Xin Liu, Palash Goyal +11
cs.AIcs.CLarXiv:2502.16111v12025
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models
Mahtab Bigverdi, Linjie Li, Weikai Huang +8
cs.AIarXiv:2606.03988v32026
When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs
Zhuoran Zhang, Tengyue Wang, Xilin Gong +4
cs.AIarXiv:2511.02243v12025
Evaluating Text-to-Visual Generation with Image-to-Text Generation
Zhiqiu Lin, Deepak Pathak, Baiqi Li +5
cs.CVcs.AIcs.CLarXiv:2404.01291v22024
Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
Qilong Wang, Jiangtao Xie, Wangmeng Zuo +2
cs.CVcs.AIstat.MLarXiv:1904.06836v22019
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
Zisu Huang, Jingwen Xu, Yifan Yang +13
cs.AIarXiv:2605.23899v12026
KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
Hancheng Ye, Zhengqi Gao, Mingyuan Ma +8
cs.MAcs.AIstat.MLarXiv:2510.12872v22025
Game-Theoretic Modeling of Driver and Vehicle Interactions for Verification and Validation of Autonomous Vehicle Control Systems
Nan Li, Dave Oyler, Mengxuan Zhang +3
cs.AIcs.GTarXiv:1608.08589v12016
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
Yuxiang Zhang, Jiangming Shu, Ye Ma +3
cs.AIarXiv:2510.12635v32025
Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Jianwei Yang, Hao Zhang, Feng Li +3
cs.CVcs.AIcs.CLarXiv:2310.11441v22023
EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning
Shihan Dou, Shaofan Liu, Zhonghang Lu +8
cs.AIcs.CLarXiv:2609.35290v12026

Artificial Intelligence

The Alignment Problem from a Deep Learning Perspective

Mathematical exploration and discovery at scale

An improvement of the convergence proof of the ADAM-Optimizer

Guided scenarios with simulated expert personae: a remarkable strategy to perform cognitive work

BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

Adaptive Code Generation for Controlling Robots

Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval

Factuality Challenges in the Era of Large Language Models

HARBOR: Automated Harness Optimization

SciFact-Open: Towards open-domain scientific claim verification

Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation

Diffsound: Discrete Diffusion Model for Text-to-sound Generation

Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models

MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

Federated Learning with Label Distribution Skew via Logits Calibration

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values

CoVer: Conflict-Aware Claim Verification

How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies

Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework

CLEAR: Continuous Latent Adapter Routing for Utility-Preserving LLM Safety Alignment

Threats, Attacks, and Defenses in Machine Unlearning: A Survey

Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

Repo2Skill-Evo: Repository Skills Go Stale in Silence

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

RLIF: Interactive Imitation Learning as Reinforcement Learning

What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis

V-STaR: Training Verifiers for Self-Taught Reasoners

Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks

People construct simplified mental representations to plan

Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning

Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning

Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback

Stop Comparing LLM Agents Without Disclosing the Harness

Writing for the Reviewer: Defensive Writing in GPT Models

Reinforcement Learning: A Survey

Learning to Watermark LLM-generated Text via Reinforcement Learning

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

Value-Decomposition Networks For Cooperative Multi-Agent Learning

Frontier Learning: Training LLM Reasoners at the Edge of Capability

On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited

Removing RLHF Protections in GPT-4 via Fine-Tuning

ASTAR: Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora

LLM-Driven Algorithm Design for Quantum Circuit Synthesis based on Binary Decision Diagrams

TessIndex: Capability Verified Identity System for the Agent Economy

One-Shot Generalization in Deep Generative Models

ResidualAuth: What Authorization State Must Language Agents Preserve under Revocable Delegation?

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs

Evaluating Text-to-Visual Generation with Image-to-Text Generation

Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization

From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

Game-Theoretic Modeling of Driver and Vehicle Interactions for Verification and Validation of Autonomous Vehicle Control Systems

Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks

Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning