G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation Paper • 2611.13004 • Published 6 days ago • 40
PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models Paper • 2611.16748 • Published 2 days ago • 41
Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models Paper • 2611.06817 • Published 4 days ago • 37