AI Research Papers
Explore the latest research papers from arXiv in artificial intelligence, machine learning, and related fields. Discover cutting-edge research from top institutions and researchers worldwide. Total: 27248 papers — Page 214 of 545
My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning
Oct 1, 2026
13 authors
cs.CL
PhysicsLENS: Diagnosing Physical Property Blindness in Video Generation Models
Oct 1, 2026
6 authors
cs.CVcs.RO
Persistent Depth Ordering amid Shifting Block-Bypass Responses in Language Model Pretraining
Oct 1, 2026
3 authors
cs.LGcs.CL
CineMR: Tool-Integrated Vision-Language Reasoning for Quantitative Cardiac MRI Assessment
Oct 1, 2026
9 authors
cs.CVcs.AI
Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability
Oct 1, 2026
5 authors
cs.LGcs.AIcs.DB
HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix
Oct 1, 2026
8 authors
cs.CL
Rethinking the Information Bottleneck: Structured Decomposition under Label-Induced Partitions
Oct 1, 2026
5 authors
cs.LG
Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models
Oct 1, 2026
2 authors
cs.CLcs.AIcs.LG
Skeleton-and-Strategy Prompting: Training-Free Negation Understanding for Vision-Language Models
Oct 1, 2026
3 authors
cs.CV
Fully Online Decentralized Learning in Stochastic Games with Unknown Independent Chains
Oct 1, 2026
1 authors
cs.LGcs.GTcs.MA+2
ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning
Oct 1, 2026
11 authors
cs.CRcs.AIcs.CL
When Does Exercise-Specific Joint Selection Help? An Audit of Evaluation and Control Design
Oct 1, 2026
4 authors
cs.AI
Counterfactual Generation via Flow Matching: Coupling-Sensitive End-to-End Rates
Oct 1, 2026
3 authors
cs.LGcs.AImath.ST+1
Semantic RGB--Depth Based Surgical Skill Assessment in Microscopic Stereo Videos
Oct 1, 2026
6 authors
cs.CV
Resolving Mixed Single-Photon LiDAR Returns for Foreground-View and Hidden Scene Reconstruction
Oct 1, 2026
8 authors
cs.CV
EgoFound3R: End-to-End Egocentric Hand Reconstruction in World Space with Point-Wise Interaction Attributes
Oct 1, 2026
5 authors
cs.CV
AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation
Oct 1, 2026
6 authors
cs.CL
Reputation, Strategy, and Emotion Effects on Generative AI Cooperation: A Comparison Across Reasoning and Non-Reasoning Models
Oct 1, 2026
6 authors
cs.AI
Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series
Oct 1, 2026
1 authors
cs.LGcs.AI
Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning
Oct 1, 2026
2 authors
cs.LGcs.RO
Judgement in the Age of Jev: From Evaluation Scarcity to Evaluation Abundance
Oct 1, 2026
1 authors
cs.CYcs.AI
Inherited Learning in an Artificial Ecology: How Controls and Update Allocation Shape Benefits
Oct 1, 2026
3 authors
cs.NE
Flow Matching Reinforcement for 3D Mesh Generation via Dynamic Homing Optimization
Oct 1, 2026
9 authors
cs.CV
ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note Generation
Oct 1, 2026
8 authors
cs.CL
Learning to Ask: Information Acquisition for SLM-LLM Collaboration, under a budget
Oct 1, 2026
3 authors
cs.AI
Evaluating the Robustness of Japanese LLMs to IME-Related and Typographical Errors
Oct 1, 2026
2 authors
cs.CL
When the Judge Acts: Auditing VLM-Guided Image Selection on Culturally Situated Prompts
Oct 1, 2026
1 authors
cs.CVcs.AIcs.CY
Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration
Oct 1, 2026
7 authors
cs.CL
Context-Aware Error Mitigation Orchestration for Hybrid Quantum Reinforcement Learning on NISQ Systems
Oct 1, 2026
3 authors
cs.LGquant-ph
Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems
Oct 1, 2026
11 authors
cs.CLcs.AIcs.CY
PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots
Oct 1, 2026
5 authors
cs.ROcs.AIcs.HC+2