Associate Professor · Aerospace Engineering

Yongxin Chen

FLAIR — Foundations of Learning and Intelligent Robots

Physical AI.
Generative Models.
Control.

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
CODA E1048B
756 W Peachtree St NW
Atlanta, GA 30332
Portrait of Yongxin Chen

Current research directions

Explore our research →

Selected contributions

Selected publications →

Research in robot planning, generative learning, and mathematical foundations.

Physical AI & robotics

Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models

Utkarsh A. Mishra, Shangjie Xue, Yongxin Chen, and Danfei Xu

Composing skill-level diffusion models generates long-horizon manipulation plans for unseen task combinations.

GSC · CoRL 2023

Generative models & learning

Scaling Reinforcement Learning for Diffusion Models via Velocity Matching

Jaemoo Choi, Wei Guo, Yuchen Zhu, Arash Vahdat, Molei Tao, Julius Berner, and Yongxin Chen

Reward-based velocity matching adapts diffusion models through updates to their velocity fields.

RVM · Preprint · 2026

Generative models & learning

Fast Sampling of Diffusion Models with Exponential Integrator

Qinsheng Zhang and Yongxin Chen

Exponential integrators exploit the structure of diffusion dynamics to reduce sampling steps.

DEIS · ICLR 2023

Sampling & stochastic control

Path Integral Sampler: A Stochastic Control Approach for Sampling

Qinsheng Zhang and Yongxin Chen

A stochastic-control formulation learns diffusion dynamics that sample from unnormalized target distributions.

PIS · ICLR 2022

Sampling & mathematical foundations

Improved Dimension Dependence of a Proximal Algorithm for Sampling

Jiaojiao Fan, Bo Yuan, and Yongxin Chen

Approximate rejection sampling improves the dimension dependence of proximal sampling across a broad class of target distributions.

Proximal sampler · COLT 2023

Control & mathematical foundations

Stochastic Control Liaisons: Richard Sinkhorn Meets Gaspard Monge on a Schrödinger Bridge

Yongxin Chen, Tryphon T. Georgiou, and Michele Pavon

A survey connecting stochastic control, optimal transport, Schrödinger bridges, and Sinkhorn algorithms.

Schrödinger bridges · SIAM Review · 2021

Selected honors

Latest news

News archive →

FLAIR Lab

Join the group

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

A brief biography

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 →