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: 26785 papers — Page 282 of 536
Evidence-Inference Reconstruction: When The Evidence Is Recalled But The Reasoning Goes Wrong
Sep 27, 2026
2 authors
cs.AI
Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning
Sep 27, 2026
6 authors
cs.LGcs.AIcs.CL
Larry Caused the Car to Stop, But the Model Didn't Notice: Transformer Blindness to the M-Heuristic
Sep 27, 2026
2 authors
cs.CL
Is your uncertainty map wrong, or is its target? Exact diagnostics for the Tweedie diagonal, and a gradient-free alternative
Sep 27, 2026
2 authors
cs.AI
LA-CPD: Local-Evidence-Aware Change-Point Detection for Human-LLM Authorship Segmentation
Sep 27, 2026
8 authors
cs.CL
Multi-Aperture PPG with MAPIS: Spatial Optical and Temporal Coherence Fields
Sep 27, 2026
2 authors
physics.opticscs.CV
Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG
Sep 27, 2026
3 authors
cs.CLcs.IRcs.LG
Do We Really Need KL Divergence for On-Policy Distillation of Large Language Models?
Sep 27, 2026
14 authors
cs.LGcs.AI
RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation
Sep 27, 2026
3 authors
cs.SEcs.CRcs.LG
MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception
Sep 27, 2026
7 authors
cs.LGcs.AIcs.CV+1
CodeActionBench: Evaluating Agentic Code-as-Policy for Embodied Manipulation
Sep 27, 2026
5 authors
cs.ROcs.AI
Controlling Speaking Rate in Autoregressive TTS via Activation Steering
Sep 27, 2026
7 authors
cs.SDcs.CLcs.LG+1
Eyes on the Road: A Naturalistic Comparison of MTW Rider Gaze in Urban Indian Traffic
Sep 27, 2026
3 authors
cs.CV
Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models
Sep 27, 2026
2 authors
cs.SEcs.LG
Annealed Sinkhorn with Momentum: Certified Unregularized Optimal Transport in Linear Memory
Sep 27, 2026
2 authors
math.OCcs.LG
Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memory
Sep 27, 2026
4 authors
cs.AI
Achieve What You Imagined: Learning to Align Actions with Visual Plans
Sep 27, 2026
8 authors
cs.ROcs.AIcs.LG
One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs
Sep 27, 2026
5 authors
cs.CVcs.LG
CLIMB-flow: Coupled Linear Inverse posterior sampling via Multiscale-Based flow
Sep 27, 2026
3 authors
cs.CVcs.LG
An Active-Bottleneck Mechanism for Weak-to-Strong Generalization
Sep 27, 2026
2 authors
stat.MLcs.AIcs.LG
DeltaSeek: Toward Active Perception in Evolving Construction Environments
Sep 27, 2026
2 authors
cs.ROcs.CV
ChemOPD: Multi-Teacher On-Policy Distillation for Multi-Task Chemical Reasoning
Sep 27, 2026
5 authors
cs.LGcs.CL
Laya as a Typed Probabilistic Assessor: An Independent Reproduction and a Preregistered Study of Calibration and Selective Escalation
Sep 27, 2026
1 authors
cs.AIcs.CLcs.LG
How code helps different tasks? A decompositional lens on LLM post-training
Sep 27, 2026
7 authors
cs.AI
QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents
Sep 27, 2026
12 authors
cs.LGcs.DC
Probability Contracts: Accuracy, Coherence, and Decisions Across LLM Interfaces
Sep 27, 2026
2 authors
cs.LGstat.ML
Rethinking Contextualization by Reinterpreting Attention Head Channels
Sep 27, 2026
6 authors
cs.LGcs.CL
ReDrive: Shaping Representations with World Modeling for End-to-End Driving
Sep 27, 2026
7 authors
cs.CV
PI-NOMT: Physics-Informed Neural Optimal Mass Transport for Brain Fluid Dynamics
Sep 27, 2026
4 authors
cs.LGcs.AI
In-Context Adaptation of Encoder-Decoder Models in Speech Recognition
Sep 27, 2026
3 authors
cs.CLcs.SDeess.AS
When Successful Strategies Fail: Adaptation to Environmental Novelty in Terminal Agents
Sep 27, 2026
5 authors
cs.AI
Population Physics, Population Problems: Safety and Emergence in LLM Societies
Sep 27, 2026
1 authors
cs.MAcs.CL
Robot-GST: geometry-aware spatial-temporal robot policy representation and evaluation
Sep 27, 2026
9 authors
cs.ROcs.AIcs.LG
Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents
Sep 27, 2026
5 authors
cs.SEcs.AIcs.LG