GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning Paper • 2606.17480 • Published 9 days ago • 3
SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction Paper • 2606.15659 • Published 11 days ago • 3
GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning Paper • 2606.17480 • Published 9 days ago • 3
SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction Paper • 2606.15659 • Published 11 days ago • 3
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects Paper • 2606.15133 • Published 12 days ago • 72
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects Paper • 2606.15133 • Published 12 days ago • 72
MotionVLA: Vision-Language-Action Model for Humanoid Motion Paper • 2606.15142 • Published 12 days ago • 4
WorldOlympiad: Can Your World Model Survive a Triathlon? Paper • 2606.11129 • Published 16 days ago • 31
PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps Paper • 2606.01788 • Published 24 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