Research

I'm a full-stack roboticist -- I believe robotics must be solved through progress in many different integral components. While scaling up data collection is important, we also need to design the right hardware (e.g, manipulators and contact sensors) and learning algorithms (e.g., learning from imbalanced sensor data) to enable robust policies on real robots for contact-rich tasks. To this end, my research includes:

• Policy learning (e.g., imitation learning, reinforcement learning) for contact-rich tasks;
• Hardware design (e.g., manipulators, data collection systems, and contact sensors) and task-driven hardware optimization;
• Learning from multi-sensor and imbalanced data;
• Human-in-the-loop policy learning and deployment;

My full research statement will be available soon.

News

• [Jan 2026] Three papers and a workshop are accepted to ICRA 2026! I am co-organizing the Workshop on RL in the Era of IL.
• [Sep 2025] I successfully defended my thesis "Diversifying Data for Contact-Rich Manipulation: Sensors, Kinematics, and Human Factors". I deeply appreciate my thesis defense committee, Sami Haddadin, Ken Goldberg, Yunzhu Li, Shuran Song, and Matei Ciocarlie for the insightful discussion.
• [Jun 2025] We gave several demos of our newly designed ROAMHand3, equipped with our dynamic tactile sensors and F/T sensors in several places, including: NEMS2025, Columbia AI Summit 2025, and General Motor Innovation Day 2025.
• [May 2025] Our paper on active acoustic tactile sensing is accepted by IROS 2025.
• [Apr 2025] I gave an invited talk at the CAIT 2025 Spring Symposium. Title: Robotic Manipulation using Low-Cost Force/Torque Sensing.
• [Sep 2024] I gave an invited talk at the MIT CSL Seminar. Host: Pulkit Agrawal.
• [Jul 2024] I gave two invited talks with the title "Co-designing Robots with Reinforcement Learning" at RSS 2024 workshop on Embodiment-aware Robot Learning and ICRA 2024 co-design workshop.
• [Jun 2024] Our paper about optimizing underactuated tentacle robots is accepted by IROS 2024.
• [Jan 2024] Two papers (hardware-policy co-design and learning human-in-the-loop policy) are accepted by ICRA 2024.
• [Jan 2023] My internship project Pick2Place is accepted by ICRA 2023!
• [Jun 2022] I started my summer internship as a research intern at Samsung AI Center NY.
• [May 2022] DiscoSyn and UMPNet are presented at ICRA 2022!

Publications (* - indicates equal contributions and joint-first authors)

Service, Teaching, and Mentoring

Academic Services

• Submission Chair: RSS 2026
• I am a long-term (>= 4 years) reviewer for: CoRL, ICRA, IROS, RSS, RA-L, TMECH, IJRR, and T-RO

Teaching Experience

• Invited Lecturer: MECE 6616 Robot Learning 2024Spring, 2025Spring
• Teaching Assistant: MECE 6616 E Robot Learning 2020Spring, 2022Spring
• Teaching Assistant: CS111 Introduction to Computer Science

Current Mentees

• Hua-Hsuan Liang (MS CS)
• Edward Zhang (UG CS)
• William Wang (UG EE)

Former Mentees

• Yifeng Cao (MS EE → Ph.D at Virginia Tech)
• Toby Kreiman (UG CS → Ph.D at UC Berkeley)
• Andrew Liu (UG CS → AI intern at Flagship Pioneering)
• Siddharth Singi (MS ME → ML Scientist at Memorial Sloan Kettering Cancer Center)
• Alvin Pan (MS CS → AI Scientist at Faction Imaging Inc.)
• Rohan James (MS CS → ML Engineer at AWS)

Software

I was a member of rlworkgroup and took part in development of several robot-learning-related open-source projects.

• Garage: A toolkit for reproducible reinforcement learning research.
• Dowel: A little logger for machine learning research.
• Meta-World: A collection of environments for benchmarking meta-learning and multi-task reinforcement learning algorithms.