- AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies, CoRL 2025
- ViTaSCOPE: Visuo-tactile Implicit Representation for In-hand Pose and Extrinsic Contact Estimation, RSS 2025
- RACER: Rich Language-guided Failure Recovery Policies for Imitation Learning, ICRA 2025
- Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities, ICLR 2025
- Neural Inverse Source Problems, CoRL 2024
Awards:
- RACER won the Best Overall Award at UM AI Symposium 2024
Organizing:
- Co-organizing Human-to-Robot workshop at CoRL 2025
Research Experience
Working in the Manipulation and Machine Intelligence (MMINT) Lab at the University of Michigan. Previously worked with Prof. Joyce Chai in the Situated Language and Embodied Dialogue (SLED) Lab.
Education
Degree: MS; School: University of Michigan – Ann Arbor; Advisor: Professor Nima Fazeli; Major: Robotics; Year: 2nd year. Bachelor's: Electronic and Information Engineering; School: Imperial College London; Advisor: Professor Ad Spiers; Lab: Manipulation and Touch Lab.
Background
Research Interests: Robot learning, robotic manipulation, and spatial intelligence. Bio: Jayjun Lee is a PhD student in Robotics at the University of Michigan. His research focuses on developing algorithms for robots to perceive and interact with the physical world, particularly multi-modal perception (e.g., vision, tactile, F/T, language, audio) and learning representations to acquire contact- and force-rich manipulation skills.
Miscellany
Contact: jayjun [at] umich [dot] edu; Links to GitHub, Google Scholar, Twitter, etc. available on personal website.