FLAIRGEORGIA TECH

FLAIR · Research

Foundation models for physical intelligence

Our goal is general-purpose physical intelligence: robots that learn from experience, predict the consequences of their actions, and solve tasks that unfold over many steps.

Physical AI and robotics

How can robots move beyond individual skills to solve unfamiliar, extended tasks?

We investigate the models and learning algorithms needed to connect perception with physical action. Our current research brings together robot foundation models, world models, reinforcement learning, and agentic robotics.

Current directions

Robot foundation models

Learning representations and policies that connect vision, language, and action. We investigate how models can transfer skills across tasks and environments.

World models

Learning generative models of how the physical world evolves. We study physical prediction and spatial reasoning as tools for planning and learning from interaction.

Reinforcement learning & post-training

Improving generative policies through reward and interaction. We investigate how to adapt pretrained models while making effective use of experience.

Agentic robotics

Bringing memory, reasoning, exploration, and planning into robotic systems. We study how robots can combine reusable skills and adapt their plans over long horizons.

Our work on compositional planning studies how learned skills and local generative models can be combined into coherent long-horizon behavior. GSC and CDGS provide two approaches to this problem.

Selected contributions

Generative models and learning

How can generative models learn from feedback and sample efficiently?

We develop algorithms for diffusion and flow models, from reward-based adaptation to sampling in continuous and discrete spaces. These methods connect our work in generative AI and robotics, while addressing questions about generation and inference in their own right.

RVM studies reinforcement learning through velocity matching. DEIS uses exponential integrators to reduce the number of steps needed to sample from diffusion models.

Selected contributions

Further work includes DMPO for reasoning in diffusion language models and the design of reinforcement learning for diffusion models.

Stochastic control and mathematical foundations

How can we generate, steer, and reason about probability distributions?

We study stochastic control, optimal transport, Schrödinger bridges, sampling, and optimization. Our goal is to understand the mathematical structure of learning and decision-making, and use that structure to design algorithms with provable properties.

This research spans sampling complexity, the control of distributions, and uncertainty in dynamical systems. It supports our Physical AI program and advances theory and methods across control, inference, and machine learning.

Selected contributions

Explore PIS and the connection between sampling and stochastic control, probabilistic reachability analysis, and adjoint Schrödinger bridge sampling.

Explore the work

Find papers, implementations, and opportunities to work with FLAIR.