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 105 of 555
Emergent Loop Geometry in Gauge-Equivariant Graph Neural Networks
Oct 13, 2026
2 authors
cond-mat.stat-mechcond-mat.str-elcs.LG+1
SolBehave: Evaluating the Behavioural Correctness of LLM-Generated Smart Contracts
Oct 13, 2026
7 authors
cs.SEcs.AI
PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards
Oct 13, 2026
8 authors
cs.SEcs.AIcs.CL
Looking Complete Is Not Being Grounded: Evaluating LLM Sitreps Against Human-Authored Situation Reports
Oct 13, 2026
1 authors
cs.CLcs.CYcs.SI
LayerCanvas: Infographic Generation in AI Learning Assistants via Hybrid Layer-Set Diffusion
Oct 13, 2026
5 authors
cs.CV
Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges
Oct 13, 2026
2 authors
cs.CL
MIST: Multi-Scale Spatial Context for Gene Expression Prediction from Histology
Oct 13, 2026
4 authors
cs.CV
BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems
Oct 13, 2026
3 authors
cs.AIcs.CL
Designing for Prediction: Planning Formulas for Expected Out-of-Sample $R^2$ and $r$
Oct 13, 2026
1 authors
stat.MEstat.ML
Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents
Oct 13, 2026
3 authors
cs.AIcs.CL
Where Do LLM Ensemble Gains Come From? Decomposing Candidate Value, Diversity, and Aggregation
Oct 13, 2026
1 authors
cs.CLcs.AI
Trust Before Autonomy: Rethinking Agentic Remote Sensing for Crisis Response
Oct 13, 2026
7 authors
cs.CVcs.CY
Registration is a Representation Problem: Solving Whole-Body PET/CT Registration
Oct 13, 2026
2 authors
cs.CVcs.LG
SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection
Oct 13, 2026
9 authors
cs.LGcs.CL
Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning
Oct 13, 2026
2 authors
cs.MAcs.AIcs.RO+1
Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs
Oct 13, 2026
3 authors
cs.CLcs.AI
DuplexBridge: Coordinating Understanding and Generation for Unified Image Editing
Oct 13, 2026
5 authors
cs.CV
Joint Neural Posterior Estimation and Model Selection for Chemical Reaction Networks
Oct 13, 2026
5 authors
stat.MLcs.LGphysics.chem-ph
WorldOracle: Benchmarking Action-Conditioned World Models against Real-World Executions
Oct 13, 2026
16 authors
cs.ROcs.CV
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding
Oct 13, 2026
8 authors
cs.CVcs.CLcs.MM
Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?
Oct 13, 2026
9 authors
cs.CV
RoboSimStudio: An Interactive Toolkit for Rapid Real2Sim of Robot Manipulation Tasks
Oct 13, 2026
12 authors
cs.ROcs.AIcs.GR+1
Plan-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds?
Oct 13, 2026
11 authors
cs.CV
Who Improves the Robot? Toward Physical Recursive Self-Improvement
Oct 13, 2026
30 authors
cs.AIcs.LGcs.RO
LIBERO-RIG: A Hardware-Setup Robustness Benchmark for Vision-Language-Action Models
Oct 13, 2026
9 authors
cs.ROcs.AI
RepProbe: Can Video Language Models Count Repeated Actions? A Diagnostic Benchmark
Oct 13, 2026
2 authors
cs.CV
The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement
Oct 13, 2026
9 authors
cs.CVcs.CL
WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World
Oct 13, 2026
5 authors
cs.CV
Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards
Oct 13, 2026
5 authors
cs.LGcs.AI
Exact Topological Compliance: Generating Persistence-Equivalent Graphs
Oct 13, 2026
3 authors
cs.LGmath.AT
Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMs
Oct 13, 2026
4 authors
cs.CV