PEEK: Picking Essential frames via Efficient Knowledge distillation Paper • 2605.31029 • Published 7 days ago • 19
SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer Paper • 2605.30409 • Published 8 days ago • 36
Category-Level 3D Correspondence in Camera Space via Morphable Object Priors Paper • 2605.28257 • Published 9 days ago • 9
SOD: Step-wise On-policy Distillation for Small Language Model Agents Paper • 2605.07725 • Published 28 days ago • 25
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time Paper • 2604.11626 • Published Apr 13 • 102
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents Paper • 2604.07430 • Published Apr 8 • 189