Generalized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding Paper • 2610.29552 • Published 6 days ago • 8
Orbia: Do Generated Videos Form a Consistent 3D World? Paper • 2610.20693 • Published 13 days ago • 50
MJev-Spatial: System One Spatial Intelligence via Native Attention Matching Paper • 2610.22276 • Published 12 days ago • 415
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing Paper • 2609.37334 • Published 28 days ago • 46
ALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video Editing Paper • 2610.08779 • Published 21 days ago • 12
Towards Looped Models Done Right, Part II: Rethinking at Fixed Points Paper • 2610.06833 • Published 22 days ago • 37
An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning Paper • 2609.35505 • Published 29 days ago • 32
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR Paper • 2609.37868 • Published 28 days ago • 65