4 papers
PrT-Flow: Probability-Tractable Flow Matching for Reinforcement Learning
Congzhong Sun, Ning Tan
Diffusion models and Flow Matching can represent flexible distributions over robot actions, but many reinforcement learning algorithms also require the probability of each action.…
ELECT: Settling Identity Before Rendering for Scalable Story Visualization
Mehrajul Abadin Miraj, Md. Mahmudul Hasan, Meherun Farzana +9
Training-free story visualization without reference images must preserve recurring entities across frames while scaling to long narratives. Existing methods typically maintain cons…
SpaceDex: Generalizable Dexterous Grasping in Tiered Workspaces
Wensheng Wang, Chuanjun Guo, Wei Wei +2
Generalizable grasping with high-degree-of-freedom (DoF) dexterous hands remains challenging in tiered workspaces, where occlusion, narrow clearances, and height-dependent constrai…
HybridGen: VLM-Guided Hybrid Planning for Scalable Data Generation of Imitation Learning
Wensheng Wang, Ning Tan
The acquisition of large-scale and diverse demonstration data are essential for improving robotic imitation learning generalization. However, generating such data for complex manip…