Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published 4 days ago • 52
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published 5 days ago • 76
Tetris3D: 3D Scene Generation With Objects That Fit Together Paper • 2610.10539 • Published 5 days ago • 45
World Observer: Joint Actor-Observer Generation for Persistent World Modeling Paper • 2610.02162 • Published 11 days ago • 89
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering Paper • 2609.38177 • Published 13 days ago • 74
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering Paper • 2609.38177 • Published 13 days ago • 74
ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition Paper • 2607.25565 • Published Jul 28 • 65
Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction Paper • 2605.26230 • Published May 25 • 38
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking Paper • 2605.12587 • Published May 12 • 37