Hi! I’m Wen-Han. I am an incoming MS Robotics student at CMU RI and an incoming Research Scientist Intern at Genesis AI. Previously, I was a visiting student at Berkeley AI Research (BAIR), where I was advised by Trevor Darrell, Koushil Sreenath and Haozhi Qi. I received my BS in MechE at NTHU.

My research interests center around:

• Embodied AI
• Robot Learning
• Dexterous Manipulation

Outside of research, I love playing basketball 🏀 & singing 🎤.

Feel free to contact me by email or Linkedin, I am happy to have a coffee chat : )

Selected Publications

(*: Equal contribution. Co-first Author.)

Learning Dexterous Manipulation Skills from Imperfect Simulations

Elvis Hsieh*, Wen-Han Hsieh*, Yen-Jen Wang*, Toru Lin, Jitendra Malik, Koushil Sreenath†, Haozhi Qi†

IEEE International Conference on Robotics and Automation (ICRA), 2026

pdf code page

Do What? Teaching Vision-Language-Action Models to Reject the Impossible

Wen-Han Hsieh*, Elvis Hsieh*, Dantong Niu, Trevor Darrell, Roei Herzig, David M. Chan

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025

pdf code page

LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery

Jerome Quenum*, Wen-Han Hsieh*, Tsung-Han Wu, Ritwik Gupta, Trevor Darrell, David M. Chan

Advanced in Neural Information Processing Systems (NeurIPS) , 2025

pdf code page

Optimizing TD3 for 7-DOF Robotic Arm Grasping: Overcoming Suboptimality with Exploration-Enhanced Contrastive Learning

Wen-Han Hsieh, Jen-Yuan Chang

International Conference on Knowledge Innovation and Invention (ICKII), 2024
Best Paper Award

pdf code