Robot foundation models
Learning representations and policies that connect perception, language, and action.
FLAIR LAB · GEORGIA TECH
Foundations of Learning And Intelligent Robots
We develop foundation models and learning algorithms for intelligent physical systems. Our work connects robot learning, generative modeling, and control to advance the capabilities of robots.
WHERE WE ARE HEADING
Learning representations and policies that connect perception, language, and action.
Generative representations for physical prediction and planning.
Adapting generative policies through interaction and reward.
Reasoning, memory, and reusable skills for extended tasks.
IDEAS INTO ALGORITHMS
Physical AI & robotics
Composing skill-level diffusion models generates long-horizon manipulation plans for unseen task combinations.
CoRL 2023
Explore project →Generative models & learning
Reward-based velocity matching adapts diffusion models through updates to their velocity fields.
Preprint · 2026
Explore project →Generative models & learning
Exponential integrators exploit the structure of diffusion dynamics to reduce sampling steps.
ICLR 2023
Explore project →Sampling & stochastic control
A stochastic-control formulation learns diffusion dynamics that sample from unnormalized target distributions.
ICLR 2022
Explore project →Sampling & mathematical foundations
Approximate rejection sampling improves the dimension dependence of proximal sampling across a broad class of target distributions.
COLT 2023
Explore project →Control & mathematical foundations
A survey connecting stochastic control, optimal transport, Schrödinger bridges, and Sinkhorn algorithms.
SIAM Review · 2021
Explore project →THE PEOPLE BEHIND THE WORK
We bring together researchers in robotics, machine learning, and mathematical foundations.
BUILD WITH US
We welcome students with strong mathematical or coding backgrounds and a curiosity about intelligent physical systems.
Join FLAIR →