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 82 of 555
HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation
Oct 14, 2026
5 authors
cs.CLcs.AIcs.CY+1
Learning When to Trust Medical Knowledge: Regression-Safe Routing for Clinical Reasoning
Oct 14, 2026
3 authors
cs.AI
MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations
Oct 14, 2026
11 authors
cs.AIcs.LG
MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction
Oct 14, 2026
5 authors
cs.CV
Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning
Oct 14, 2026
9 authors
cs.LGcs.CL
Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
Oct 14, 2026
9 authors
cs.CLcs.AI
Function-Space Temporal Self-Distillation for Policy Optimization
Oct 14, 2026
3 authors
cs.LGcs.AIcs.CL+1
PPAD-Completeness of Contiguous Envy-Free Cake Cutting with Additive Valuations
Oct 14, 2026
3 authors
cs.GTcs.AIcs.MA
ReFormBench: Benchmarking the Stability of Response-Conditioned Format Correction in Large Language Models
Oct 14, 2026
6 authors
cs.AI
C3: Rethinking Process Supervision via Confidence-Guided Credit Correction in Multi-Turn Reinforcement Learning
Oct 14, 2026
8 authors
cs.AI
Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models
Oct 14, 2026
8 authors
cs.CL
ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning
Oct 14, 2026
6 authors
cs.LG
BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla
Oct 14, 2026
3 authors
cs.CL
RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing
Oct 14, 2026
5 authors
cs.CL
Graph Additive Models disentangling feature, topology, and interactions
Oct 14, 2026
6 authors
stat.MLcs.LG
SceneAE: Scene Generation and Reconstruction in Queryable 3D-Anchored Latent Space
Oct 14, 2026
6 authors
cs.CVcs.AI
New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents
Oct 14, 2026
7 authors
cs.LGcs.AI
Uncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies
Oct 14, 2026
5 authors
cs.ROcs.AIcs.MA
No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation
Oct 14, 2026
5 authors
cs.CVcs.CR
Learning Individual Scientific Taste with Privileged Hindsight Distillation
Oct 14, 2026
6 authors
cs.AIcs.LG
ONCship: A Large-Scale Underwater Acoustic Corpus for Ship Recognition
Oct 14, 2026
3 authors
cs.SDcs.AIeess.SP
Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding
Oct 14, 2026
3 authors
cs.CLcs.AIcs.CV
TimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models
Oct 14, 2026
7 authors
cs.LG
Mitigating Video Hallucinations via Attention-Guided Representation Perturbation
Oct 14, 2026
7 authors
cs.CVcs.AIcs.CL
A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics
Oct 14, 2026
3 authors
cs.CV
What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization
Oct 14, 2026
4 authors
cs.LGcs.AIcs.RO
Controlling the latency in temporal coded spiking models for neuromorphic datasets
Oct 14, 2026
2 authors
cs.NE
Exact Cut Complexity of Equal-Length Proportional Cake Cutting
Oct 14, 2026
3 authors
cs.MAcs.AIcs.DS+1
MakSafe: A Spatiotemporal Semantic Framework for Formal Specification and Compliance Checking of Road Vehicle Safety Rules
Oct 14, 2026
4 authors
cs.CLcs.SC
Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs
Oct 14, 2026
2 authors
cs.CLcs.AI
HyperLoop: Hyperspectral-Assisted Loop Closure Detection in 3D-SLAM for Planetary Exploration
Oct 14, 2026
5 authors
cs.CVcs.RO
Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors
Oct 14, 2026
4 authors
cs.CVcs.LG
Beyond Reachability: A Relation-Semantic Reasoning Framework for Biomedical Multi-hop QA
Oct 14, 2026
4 authors
cs.CL
Qwen-MT-Lumen at WMT2026: Instruction-Specialized Translation via Quality-Aware Training and On-Policy Distillation
Oct 14, 2026
14 authors
cs.CL
PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making
Oct 14, 2026
3 authors
cs.CLcs.AI