5 papers
ScalingAttention: Discovering Intrinsic Sparse Attention Topology for Video Diffusion Transformers
Ruiliang Zhou, Xuecheng Wu, Kang He +6
While Diffusion Transformers (DiTs) have revolutionized high-fidelity video generation, their reliance on 3D full attention creates a quadratic computational bottleneck. Existing s…
TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation
Qinwen Xu, Jiaming Liu, Rui Zhou +11
Despite strong generalization capabilities, Vision-Language-Action (VLA) models remain constrained by the high cost of expert demonstrations and limited real-world interaction. Whi…
GenHSI: Controllable Generation of Human-Scene Interaction Videos
Zekun Li, Rui Zhou, Rahul Sajnani +3
Large-scale pre-trained video diffusion models have exhibited remarkable capabilities in diverse video generation. However, existing solutions face several challenges in generating…
Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling
Yueru Jia, Jiaming Liu, Shengbang Liu +7
Robust perception and dynamics modeling are fundamental to real-world robotic policy learning. Recent methods employ video diffusion models (VDMs) to enhance robotic policies, impr…
MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies
Chengbo Yuan, Rui Zhou, Mengzhen Liu +6
Scaling real robot data is a key bottleneck in imitation learning, leading to the use of auxiliary data for policy training. While other aspects of robotic manipulation such as ima…