G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation Paper • 2611.13004 • Published 5 days ago • 37
PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models Paper • 2611.16748 • Published 1 day ago • 30
Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models Paper • 2611.06817 • Published 3 days ago • 37