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: 27748 papers — Page 85 of 555
What Coding Agents Leave Unsaid: Measuring Task-State Gaps Between Execution and Reports
Oct 14, 2026
4 authors
cs.AI
Provable Transformer Context Compression for In-Context Reinforcement Learning
Oct 14, 2026
6 authors
cs.LGcs.AI
Minimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration bounds
Oct 14, 2026
3 authors
stat.MLcs.LGmath.ST
Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL
Oct 14, 2026
6 authors
cs.LGstat.ML
ChemArgus: Automated Scientific Diagnostics for Lab-Grade Multimodal Chemistry Reasoning: A Frontier Benchmark
Oct 14, 2026
24 authors
cs.LG
Memorizing Who, Knowing How: Benchmarking Personal and Procedural Memory for Persistent Assistants
Oct 14, 2026
8 authors
cs.AI
Weighted Adjoint Matching: Finetuning Flow Matching Models with Time-Dependent Control Cost
Oct 14, 2026
2 authors
stat.MLcs.LG
SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution
Oct 14, 2026
13 authors
cs.SEcs.AI
Sequential Learning-Based Physics-Informed Neural Network Modeling for Parameter Estimation on a Power Converter
Oct 14, 2026
4 authors
cs.LGeess.SY
CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection
Oct 14, 2026
5 authors
cs.CRcs.AI
FACES: Fine-grained Gated Semantic Alignment for Multimodal Emotional Support Conversation
Oct 14, 2026
7 authors
cs.CL
GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation
Oct 14, 2026
5 authors
cs.CVcs.AIcs.CR
Beyond Correctness: Compute-Responsive Data Selection for Reasoning Model Post-Training
Oct 14, 2026
7 authors
cs.AI
Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts
Oct 14, 2026
6 authors
cs.CLcs.AI
Trainable at Depth, Solvable at Small Size: What the Loss Surface of a Polynomial Activation Dictates for Designing, Initializing and Training Networks
Oct 14, 2026
1 authors
cs.LGcs.AI
Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow
Oct 14, 2026
7 authors
cs.LGcs.AI
GDBA-Net: A Gated Dual-Branch Adaptation of SAM2 for Robust Cross-Domain Nuclei Segmentation
Oct 14, 2026
5 authors
cs.CV
Feasibility of a Patient-Specific Digital Twin for Ventriculoperitoneal Shunt Trajectory Planning
Oct 14, 2026
5 authors
cs.CVq-bio.QM
A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization
Oct 14, 2026
3 authors
cs.LGstat.ML
VisualWorldBench: A Fine-Grained Multi-Task Benchmark for Evaluating Visual World Knowledge in MLLMs
Oct 14, 2026
3 authors
cs.CV
Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question Answering
Oct 14, 2026
5 authors
cs.AIcs.CLeess.AS
AFCS: Atomic-Fact-Conditioned Synthesis for Factual Knowledge Pretraining
Oct 14, 2026
5 authors
cs.CLcs.AI
When Pairwise Preferences Cycle: A Reliability-Anchored Preference Walk for Video GRPO
Oct 14, 2026
5 authors
cs.CV
RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation
Oct 14, 2026
3 authors
cs.CV
Task-State Governance: A Virtual Machine for Verifiable and Recoverable GUI Agent Execution
Oct 14, 2026
9 authors
cs.HCcs.AI
Language Exposure Matters: Distribution and Order in Multilingual BabyLM Pre-training
Oct 14, 2026
3 authors
cs.CL
What Do Foundation Models for Market Microstructure Learn? A Controlled Study with Synthetic Limit Order Books
Oct 14, 2026
1 authors
cs.LG
Exhaustive Canonical Skeletons Generation: A Formal Dataset for Decomposable Symbolic Regression
Oct 14, 2026
2 authors
cs.LG
RepForcing: Representation-Space Initialization for Autoregressive Video Distillation
Oct 14, 2026
6 authors
cs.CV
From Spectral to Frobenius: When Muon Loses Its Spectral Implicit Bias
Oct 14, 2026
3 authors
cs.LGcs.AI
ACR-Net: Mitigating Semantic Dominance via Contrastive Acoustic-Semantic Decoupling
Oct 14, 2026
4 authors
cs.SDcs.AI
Maximising Transparency in Context Compaction Improves Retention of Facts and Commitments for Lightweight Coding Agents
Oct 14, 2026
1 authors
cs.AI
DreamHMR: From Video Generation to Human Motion Modeling via Structural Focusing
Oct 14, 2026
3 authors
cs.CVcs.AI
Seeing at the Edge: Energy Characterization of Vision-Language Model Inference on Edge Platforms
Oct 14, 2026
4 authors
cs.LG