Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models
Composing skill-level diffusion models generates long-horizon manipulation plans for unseen task combinations.
GSC · CoRL 2023
Associate Professor · Aerospace Engineering
FLAIR — Foundations of Learning and Intelligent Robots
My goal is to build the models and algorithms that make general-purpose physical intelligence possible. At FLAIR, we develop robot foundation models, world models, and reinforcement learning methods for robots that can learn new skills, reason about their surroundings, and solve long-horizon tasks.
This research grows out of my work on generative modeling, stochastic control, optimal transport, and optimization. I continue to advance these areas through new algorithms and theory for generation, sampling, and decision-making under uncertainty.
Office address
Research in robot planning, generative learning, and mathematical foundations.
Composing skill-level diffusion models generates long-horizon manipulation plans for unseen task combinations.
GSC · CoRL 2023
Reward-based velocity matching adapts diffusion models through updates to their velocity fields.
RVM · Preprint · 2026
Exponential integrators exploit the structure of diffusion dynamics to reduce sampling steps.
DEIS · ICLR 2023
A stochastic-control formulation learns diffusion dynamics that sample from unnormalized target distributions.
PIS · ICLR 2022
Approximate rejection sampling improves the dimension dependence of proximal sampling across a broad class of target distributions.
Proximal sampler · COLT 2023
A survey connecting stochastic control, optimal transport, Schrödinger bridges, and Sinkhorn algorithms.
Schrödinger bridges · SIAM Review · 2021
FLAIR Lab
We welcome motivated graduate students interested in Physical AI, machine learning, robotics, and control. Our strategic area for Fall 2027 is Physical AI.
Please email your CV and transcripts. Visiting scholars are welcome to inquire; arrangements normally take at least two months. There are currently no funded postdoctoral positions; applicants would need external fellowship support.
Meet the group →Academic background
I am an Associate Professor in Aerospace Engineering at Georgia Tech, affiliated with the Institute for Robotics and Intelligent Machines and the Machine Learning Center. I received my BSc from Shanghai Jiao Tong University in 2011 and PhD from the University of Minnesota in 2016.
Before Georgia Tech, I held appointments at Memorial Sloan Kettering Cancer Center and Iowa State University. I also held a part-time research appointment at NVIDIA.
I delivered a plenary talk at ACC 2023 and a semi-plenary talk at MTNS 2024.
Full curriculum vitae →