π^4: A Foundation Model for 4D Scene Geometry and Motion Paper • 2611.23144 • Published 5 days ago • 19
InternW0-$Δ$: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data Paper • 2609.31394 • Published Sep 25 • 26
RoboAtom: Large-scale Atomic-Action Supervision for Robot Learning Paper • 2610.40207 • Published 24 days ago • 3
JVT: Just Video Transformer makes pixel-space video diffusion simple Paper • 2611.18549 • Published 9 days ago • 15
JVT: Just Video Transformer makes pixel-space video diffusion simple Paper • 2611.18549 • Published 9 days ago • 15
From Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face Swapping Paper • 2610.26681 • Published Oct 19 • 19
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning Paper • 2610.19789 • Published Oct 14 • 39
CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding Paper • 2609.40048 • Published Sep 30 • 13
PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training Paper • 2610.04616 • Published Oct 3 • 14
MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism Paper • 2606.07512 • Published Jun 5 • 41
Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration? Paper • 2606.01247 • Published May 31 • 29
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction Paper • 2605.26115 • Published May 25 • 55