8 papers
Humanoid Mobility via Attention-based Contacts
Junzhe He, Kehan Wen, Chong Zhang +7
Humanoid mobility over complex terrain requires accurate foot placement and coordinated whole-body motion capable of robust adaptation. Reinforcement learning (RL) policies trained…
JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics
Kehan Wen, Ziming Li, Siyuan Luo +1
Latent world models plan by predicting how candidate actions advance learned latent dynamics. In self-predictive models, however, the encoder and predictor are optimized jointly an…
RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation
Pengzhi Yang, Xinyu Wang, Pengyu Jing +7
Reinforcement learning for robot manipulation is often bottlenecked by reward design, especially in long-horizon tasks: sparse success rewards provide weak supervision, while hand-…
Learning Whole-Body Humanoid Locomotion via Motion Generation and Motion Tracking
Zewei Zhang, Kehan Wen, Michael Xu +7
Whole-body humanoid locomotion is challenging due to high-dimensional control, morphological instability, and the need for real-time adaptation to various terrains using onboard pe…
Constrained Style Learning from Imperfect Demonstrations under Task Optimality
Kehan Wen, Chenhao Li, Junzhe He +1
Learning from demonstration has proven effective in robotics for acquiring natural behaviors, such as stylistic motions and lifelike agility, particularly when explicitly defining…
Mini Diffuser: Fast Multi-task Diffusion Policy Training Using Two-level Mini-batches
Yutong Hu, Pinhao Song, Kehan Wen +1
We present a method that reduces, by an order of magnitude, the time and memory needed to train multi-task vision-language robotic diffusion policies. This improvement arises from…
MPC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model
Kehan Wen, Yutong Hu, Yao Mu +1
Recent work in Offline Reinforcement Learning (RL) has shown that a unified Transformer trained under a masked auto-encoding objective can effectively capture the relationships bet…
DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision
Yutong Hu, Kehan Wen, Fisher Yu
Learning dexterous locomotion policy for legged robots is becoming increasingly popular due to its ability to handle diverse terrains and resemble intelligent behaviors. However, j…