Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published 7 days ago • 68
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published 8 days ago • 88
Tetris3D: 3D Scene Generation With Objects That Fit Together Paper • 2610.10539 • Published 8 days ago • 48
World Observer: Joint Actor-Observer Generation for Persistent World Modeling Paper • 2610.02162 • Published 14 days ago • 90
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering Paper • 2609.38177 • Published 16 days ago • 78
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering Paper • 2609.38177 • Published 16 days ago • 78
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