RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning Paper • 2609.03199 • Published 5 days ago • 115
ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition Paper • 2607.25565 • Published Jul 28 • 66
A Quantized Native Runtime for On-Device Semantic Audio Generation Paper • 2607.08526 • Published Jul 9 • 4
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model Paper • 2607.03509 • Published Jul 3 • 14
Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems Paper • 2606.18837 • Published Jun 17 • 59
Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation Paper • 2606.19120 • Published Jun 17 • 2
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 434