Zhuowen Tu

VideoNSA: Native Sparse Attention Scales Video Understanding

Reinforce Your Layout: Online Reward-Guided Diffusion for Layout-to-lmage Generation

AuxVLA: Auxiliary Task Learning and Multi-Modal Enhancement for Vision-Language-Action Models in Mobile Manipulation

Real Deep Research from Foundation Model to Robotics

Salient Concept-Aware Generative Data Augmentation

Efficient Scaling of Diffusion Transformers for Text-to-Image Generation

Lay-Your-Scene: Open-Vocabulary Text to Layout Generation

Mousterian: exploring the equivalence of generative and real data augmentation in classification