I’m a Ph.D. candidate at the University of Michigan, advised by Stella X. Yu.
Robot learning. My research interests center on scalable robot learning from diverse data and experience. I study how perception and large-scale priors—such as human motion repertoires—can support adaptable, reliable behavior across tasks and environments. My current work focuses on contact-rich interaction and humanoid whole-body control.
Perception. I study embodied vision: understanding the world from partial observations. My interests span spatial and dynamic understanding and semantic localization, with the goal of supporting useful decisions and actions in the real world.
Seeking summer 2027 research internships in robotics and computer vision.
* Equal contribution
NeurIPS 2026
We show that learning what to match is as important as learning how to match. Our adaptive units follow coherent motion and preserve fine boundaries, making optical flow both precise and robust—even where a match is hidden or outside the image.
Under review
We turn getting back up into a behavior the robot can adapt and steer. A visual diffusion model lets us guide heading, timing, and route at test time, while a depth-aware controller carries out the recovery on a real Unitree G1.
C.-L. Hsieh*, Z. Wang*, S. X. Yu, E. Corona, S. Sasidharan, and E. D. Sumer.
NeurIPS Workshop on Long-Context Foundation Models (LCFM), 2026.
Finding a tiny part in a long video can be surprisingly difficult. HitchIt chooses useful views and tracks visual examples to locate parts such as trailer hitches without task-specific training.
Y.-C. Lo, C.-L. Hsieh, H.-W. Chiang, and A.-Y. A. Wu.
IEEE Internet of Things Journal, 12(8):11081–11095, 2025.
C.-L. Hsieh, Y.-C. Lo, and A.-Y. A. Wu.
IEEE International Workshop on Machine Learning for Signal Processing (MLSP), 2023.
Y.-C. Lo, C.-L. Hsieh, and A.-Y. A. Wu.
IEEE International Workshop on Machine Learning for Signal Processing (MLSP), 2023.
Graduate Student Instructor · University of Michigan