Leslie Kaelbling

Leslie Kaelbling is the Panasonic Professor in the Department of Electrical Engineering and Computer Science and the co-scientific director of the MIT Quest for Intelligence. She is also an investigator at the Computer Science and Artificial Intelligence Laboratory.  Her research aim is to building intelligent robots, with a focus on learning, state estimation, and planning under uncertainty. Kaelbling has previously worked at Brown University, Teleos Research, and the Artificial Intelligence Center of SRI International.  Kaelbling is the founder and first editor-in-chief of the open-access Journal of Machine Learning Research. She is also a fellow of the Association for the Advancement of Artificial Intelligence. She received a BA in philosophy and a PhD in computer science from Stanford University.

Selected Publications

• Ajay, A., Han, S., Du, Y., Li, S., Gupta, A., Jaakkola, T., Tenenbaum, J., Kaelbling, L., Srivastava, A., Agrawal, P. (2023) Compositional Foundation Models for Hierarchical Planning. Conference on Neural Information Processing Systems (NeurIPS).
• Luo, Z., Mao, J., Wu, J., Lozano-Perez, T., Tenenbaum, J., and Kaelbling, L.P. (2023). Learning Rational Subgoals from Demonstrations and Instructions. Association for the Advancement of Artificial Intelligence (AAAI)
• Silver, T., Chitnis, R., Lozano Peréz, T., Kaelbling, L.P., Tenenbaum, J., McClinton, W., Kumar, N. (2023). Predicate Invention for Bilevel Planning. Association for the Advancement of Artificial Intelligence (AAAI)
• Silver, T., Hariprasad, V., Shuttleworth, R., Kumar, N., Lozano-Perez, T., and Kaelbling, L.P. (2022). PDDL Planning With Pretrained Large Language Models. Conference and Workshop on Neural Information Processing Systems (NeurIPS) FMDM workshop.

Media

• Oct. 21, 2019: MIT News, Pushy robots learn the fundamentals of object manipulation.
• October 1, 2018: MIT News, Ideas abound at Quest for Intelligence workshop.