Video Analysis and Generation via a Semantic Progress Function Paper • 2604.22554 • Published 24 days ago • 63
Seeing Fast and Slow: Learning the Flow of Time in Videos Paper • 2604.21931 • Published 25 days ago • 19
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System Paper • 2604.14125 • Published Apr 15 • 21
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents Paper • 2604.07430 • Published Apr 8 • 187
WorldAgents: Can Foundation Image Models be Agents for 3D World Models? Paper • 2603.19708 • Published Mar 20 • 13
3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model Paper • 2603.18524 • Published Mar 19 • 58
Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models Paper • 2603.15618 • Published Mar 16 • 21
VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos Paper • 2510.19488 • Published Oct 22, 2025 • 22
RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies Paper • 2603.04639 • Published Mar 4 • 30
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics Paper • 2602.19313 • Published Feb 22 • 26
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning Paper • 2601.09708 • Published Jan 14 • 55