Assistant Professor of Computer ScienceHarvard University · Kempner Institute
I study how intelligent systems can combine reusable knowledge with inference-time reasoning to solve problems not anticipated during training.
I explore this boundary through four interfaces: search over generative solution spaces, composition of reusable models, planning with world models, and reasoning through multi-agent interaction. My long-term goal is to build physical agents that adapt reliably in unfamiliar environments.
I lead the Embodied Minds Lab at Harvard and am a part-time research scientist at NVIDIA Research. I received my PhD from MIT EECS, advised by Leslie Kaelbling, Tomas Lozano-Pérez, and Joshua B. Tenenbaum. Before Harvard, I held research roles at OpenAI and Google DeepMind.
There is no single boundary between learning and inference. Our group explores four distinct interfaces between them.
KnowledgeSolution spacesReasoningSample and refine
Generative models represent a space of possible solutions. Iterative inference lets us search that space and refine candidate solutions to improve results or meet new constraints.
Examples: deep EBMs, Reduce, Reuse, Recycle, and reasoning with sampling.
KnowledgeReusable modelsReasoningCompose and search
Reusable models capture different sources of knowledge. Composing them at inference time lets us adapt to new combinations of goals and constraints.
Examples: composable diffusion models, Diffuser, and compositional energy minimization.
KnowledgeWorld dynamicsReasoningPredict and plan
World models capture how environments evolve. Planning over possible futures lets physical agents pursue new goals and adapt to change.
Examples: UniPi, Video Language Planning, and Large Video Planner.
KnowledgeDistributed across agentsReasoningInteract and coordinate
Language models capture complementary knowledge and perspectives. Their interactions at inference time let them evaluate and refine candidate solutions.
Examples: multi-agent debate, multi-agent verification, and Economy of Minds.
* Equal contribution; † or + equal advising.