About
I am a postdoctoral researcher at The University of Hong Kong (HKU), working with Prof. Yi Ma.
My research focuses on embodied intelligence and the edge deployment of large foundation models. I study how robots can learn from interaction and adapt to real-world environments, and how foundation models can operate efficiently on devices with limited memory and computational resources. By bringing together robot learning, control, and efficient model inference, I aim to enable embodied systems that can learn, plan, and act with intelligence deployed directly on the device.
Previously, I was a postdoctoral researcher in Prof. Melanie Zeilinger’s group at ETH Zurich. I completed my PhD through the Center for Learning Systems, a joint doctoral program between the Max Planck Institute for Intelligent Systems (MPI-IS) and ETH Zurich, advised by Dr. Michael Muehlebach and Prof. Melanie Zeilinger.
Recent news
- Oct 2026: Our paper Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control was accepted at CoRL 2026.
- Oct 1, 2026: I started as a postdoctoral researcher at The University of Hong Kong (HKU), working with Prof. Yi Ma.
- Sep 30, 2026: I completed my postdoctoral appointment in Prof. Melanie Zeilinger’s group at ETH Zurich.
- Aug 2026: Our paper Efficient Model-Based Reinforcement Learning for Robot Control via Online Learning was accepted for publication in The International Journal of Robotics Research (IJRR).
- Aug 2026: I am co-organizing the NeurIPS 2026 Workshop on On-Device Intelligence: Foundation Models under Real-World Constraints in Sydney, Australia. Submissions are due August 29, 2026 (AoE).
- Apr 30, 2026: Our paper SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference was accepted to ICML 2026, which will be held in Seoul, South Korea, where I will present the poster.
- Apr 1, 2026: I started as a postdoctoral researcher in Prof. Melanie Zeilinger’s group at ETH Zurich.
- Mar 25, 2026: Our paper SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference was selected as a recent spotlight at CPAL 2026 in Tuebingen, where I presented the poster.
- Feb 2026: I taught the course Signals and Systems at Ashesi University in Ghana.
- Dec 15, 2025: I successfully defended my PhD thesis, Robot Learning under Control-Theoretic Constraints: From Offline Generalization to Online Adaptation.
- Sep 17, 2025: I presented a contributed talk at the EWRL 2025, entitled Provably Efficient Online Learning in Real-World Cyber-Physical and Robotic Systems.
- Sep 2025: Our demo proposal CRS – An Open-Source, Low-Cost, and Modular Platform for Robot Learning Research was accepted at CoRL 2025.
- Sep 2025: Our paper CRS: An Open-Source, Low-Cost, and Modular Platform for Robot Learning Research accepted at the Open-Source Hardware in Robot Learning Workshop at CoRL 2025.
- Aug 2025: Our paper Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing was accepted at CoRL 2025.
- Jul 2025: Our paper Constraint-Aware Diffusion Guidance for Imitation Learning was accepted at EWRL 2025.
- Jul 2025: Our paper Online Optimization of Closed-Loop Control Systems was accepted at EWRL 2025.