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 79 of 555
MMKG-R1: Constructing Multimodal Knowledge Graphs via Reinforcement Learning
Oct 14, 2026
8 authors
cs.CV
Why Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States
Oct 14, 2026
15 authors
cs.MAcs.AI
Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering
Oct 14, 2026
3 authors
cs.LGcs.CL
Integrated Novelty Detection Systems: From Sensor Networks to Multi-Novelty Computer Vision
Oct 14, 2026
1 authors
cs.LGcs.CV
Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents
Oct 14, 2026
4 authors
cs.LGcs.CL
Subdata Selection for Measurement-Constrained Linear Regression under Model Misspecification
Oct 14, 2026
3 authors
stat.MEstat.ML
BFHD: Bidirectional Feature Harmonization Decomposition for Heterogeneous Clinical Assessments
Oct 14, 2026
4 authors
cs.LG
Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering
Oct 14, 2026
2 authors
cs.AIcs.CLcs.LG
VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement
Oct 14, 2026
3 authors
cs.CVcs.CLcs.RO
Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems
Oct 14, 2026
3 authors
cs.CLcs.AIcs.LG
Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context
Oct 14, 2026
9 authors
cs.LG
Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory
Oct 14, 2026
80 authors
cs.AIcs.CLcs.RO
The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking
Oct 14, 2026
3 authors
cs.CVcs.LG
Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy Rewards
Oct 14, 2026
1 authors
cs.LGcs.AI
Evaluating Compressed Memory: Dependence, Utility, and Content Benefit
Oct 14, 2026
4 authors
cs.CLcs.AI
One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models
Oct 14, 2026
2 authors
cs.LG
Robust Explanatory Analysis for Structured Optimization Networks (REASON) in Learning
Oct 14, 2026
3 authors
cs.LGcs.CV
Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback
Oct 14, 2026
7 authors
cs.CL
EvoWeave: Composing Reusable Agent Experience through Operation Level Graphs
Oct 14, 2026
7 authors
cs.AI
RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning
Oct 14, 2026
5 authors
cs.LG
STRATA: Self-Maintaining Structured Experience Graphs for Self-Evolving Language Agents
Oct 14, 2026
5 authors
cs.AI
The Sum of All Summaries: PROPALIGN for Graded Proposition Salience Evaluation
Oct 14, 2026
4 authors
cs.CL
ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies
Oct 14, 2026
3 authors
cs.CLcs.AIcs.SD
Selective Next-Location Prediction with MetaModelSelect: A Lightweight Post-Hoc Confidence Metamodel
Oct 14, 2026
2 authors
cs.LGcs.NI
SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning
Oct 14, 2026
8 authors
cs.AI
KoAGE: Do Large Language Models Know, Learn, and Coin Korean Neologisms?
Oct 14, 2026
3 authors
cs.CLcs.AI
Train to Stitch: Topology-Preserving Regularization for Interoperable Representations
Oct 14, 2026
3 authors
cs.LGcs.CVeess.SP
ActMOF: Mapping Reticular Synthesis through Active Learning
Oct 14, 2026
8 authors
cond-mat.mtrl-scics.LGphysics.chem-ph
Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off
Oct 14, 2026
2 authors
cs.DCcs.AIcs.LG+1
Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers
Oct 14, 2026
3 authors
cs.CLcs.AIcs.CV
ForkGRPO: Efficient Exploration and Fine-Grained Credit Assignment for Diffusion Language Models
Oct 14, 2026
4 authors
cs.CL
W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition
Oct 14, 2026
3 authors
cs.LG
Recursive Formation and First-Class Reuse of Compositional Capabilities
Oct 14, 2026
1 authors
cs.PLcs.AI
WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding
Oct 14, 2026
9 authors
cs.CV
Latent Annealed Posterior Sampling with a Variance-Preserving Bridge for Sparsely Observed Random Fields
Oct 14, 2026
2 authors
stat.MLcs.LG
From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents
Oct 14, 2026
6 authors
cs.ROcs.AIcs.CV
Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training
Oct 14, 2026
10 authors
cs.AIcs.DC
VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness
Oct 14, 2026
13 authors
cs.CVcs.AI