MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling Paper • 2606.13473 • Published 2 days ago • 66
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Paper • 2606.08063 • Published 7 days ago • 69
VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation Paper • 2606.07723 • Published 8 days ago • 3
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published 5 days ago • 54
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories Paper • 2606.13578 • Published 2 days ago • 48
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments Paper • 2606.13681 • Published 2 days ago • 97
InterleaveThinker: Reinforcing Agentic Interleaved Generation Paper • 2606.13679 • Published 2 days ago • 71
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Paper • 2606.13673 • Published 2 days ago • 77
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents Paper • 2606.12087 • Published 3 days ago • 70
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them Paper • 2606.06361 • Published 9 days ago • 14
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence Paper • 2605.25979 • Published 19 days ago • 27
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published 22 days ago • 80
GEM: Generative Supervision Helps Embodied Intelligence Paper • 2605.28548 • Published 17 days ago • 41
ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation Paper • 2605.28293 • Published 17 days ago • 87
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 17 days ago • 423
SpatialBench: Is Your Spatial Foundation Model an All-Round Player? Paper • 2605.27367 • Published 18 days ago • 72
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding Paper • 2605.27365 • Published 18 days ago • 139
MolmoAct2: Action Reasoning Models for Real-world Deployment Paper • 2605.02881 • Published May 4 • 348