Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published 19 days ago • 73
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published 20 days ago • 92
Tetris3D: 3D Scene Generation With Objects That Fit Together Paper • 2610.10539 • Published 20 days ago • 49
EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos Paper • 2609.39378 • Published 27 days ago • 77
World Observer: Joint Actor-Observer Generation for Persistent World Modeling Paper • 2610.02162 • Published 26 days ago • 91
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering Paper • 2609.38177 • Published 28 days ago • 78
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents Paper • 2609.39982 • Published 27 days ago • 120