DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects Paper • 2606.15133 • Published 6 days ago • 7
MotionVLA: Vision-Language-Action Model for Humanoid Motion Paper • 2606.15142 • Published 6 days ago • 2
WorldOlympiad: Can Your World Model Survive a Triathlon? Paper • 2606.11129 • Published 10 days ago • 31
PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps Paper • 2606.01788 • Published 18 days ago • 9
EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory Paper • 2604.27695 • Published Apr 30
PresentAgent-2: Towards Generalist Multimodal Presentation Agents Paper • 2605.11363 • Published May 12 • 8
PresentAgent-2: Towards Generalist Multimodal Presentation Agents Paper • 2605.11363 • Published May 12 • 8
EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory Paper • 2604.27695 • Published Apr 30
Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction Paper • 2605.11354 • Published May 12 • 1
Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction Paper • 2605.11354 • Published May 12 • 1
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation Paper • 2604.24764 • Published Apr 27 • 119
MWM: Mobile World Models for Action-Conditioned Consistent Prediction Paper • 2603.07799 • Published Mar 8
OCR-Agent: Agentic OCR with Capability and Memory Reflection Paper • 2602.21053 • Published Feb 24 • 3