Xiufeng Song

DIVA: Discrete Diffusion Vision-Language-Action Models for Parallelized Action Generation

Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning

RoboMonster: Compositional Generalization of Heterogeneous Multi-End Effector Embodied Agents

Building Scalable Real-World Robot Data Generation via Compositional Simulation

On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection