Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement Paper • 2611.08318 • Published 15 days ago • 22
PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models Paper • 2611.16748 • Published 8 days ago • 43
G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation Paper • 2611.13004 • Published 12 days ago • 47
Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models Paper • 2611.06817 • Published 10 days ago • 37
PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data Paper • 2611.05320 • Published 17 days ago • 29
Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation Paper • 2610.02368 • Published Oct 1 • 55
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation Paper • 2606.28128 • Published Jun 26 • 51
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining Paper • 2606.20521 • Published Jun 18 • 13
Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving Paper • 2605.23163 • Published May 25 • 17
StableVLA: Towards Robust Vision-Language-Action Models without Extra Data Paper • 2605.18287 • Published May 18 • 15
HumanNet: Scaling Human-centric Video Learning to One Million Hours Paper • 2605.06747 • Published May 7 • 54
Enhancing Spatial Understanding in Image Generation via Reward Modeling Paper • 2602.24233 • Published Feb 27 • 56
iFSQ: Improving FSQ for Image Generation with 1 Line of Code Paper • 2601.17124 • Published Jan 23 • 34
CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance Paper • 2503.10391 • Published Mar 13, 2025 • 12
Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models Paper • 2601.07287 • Published Jan 12 • 6
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head Paper • 2601.07832 • Published Jan 12 • 53