Armando Solar-Lezama
Professor, Electrical Engineering and Computer Science; Associate Director and COO, Computer Science and Artificial Intelligence Laboratory
Who they work with
Categories
Armando Solar-Lezama is a professor in MIT’s Department of Electrical Engineering and Computer Science. He is the associate director and COO in the Computer Science and Artificial Intelligence Laboratory, where he leads the Computer Assisted Programming Group. Solar-Lezama and his research group focus on program synthesis, a research area at the intersection of programming systems and artificial intelligence. On the one hand, program synthesis is about the use of automated reasoning and learning to bring more automation to the programming process. On the other hand, code provides a uniquely versatile modeling mechanism, so program synthesis can play a powerful role in helping to build learning systems that are more predictable and robust. Solar-Lezama earned a PhD from University of California, Berkeley.
Publications
- Gao, S., Kapinski, J., Deshmukh, J. V., Roohi, N., Solar-Lezama, A., Aréchiga, N., Kong, S. (2019). Numerically-robust inductive proof rules for continuous dynamical systems. Computer Aided Verification – 31st International Conference (CAV) New York City, NY, Proceedings, Part II.
- Campos, T., Inala, J. P., Solar-Lezama, A., Kress-Gazit, H. (2019). Task-based design of ad-hoc modular manipulators. International Conference on Robotics and Automation (ICRA) Montreal, QC, Canada.
- Nye, M. I., Hewitt, L. B., Tenenbaum, J. B., Solar-Lezama, A. (2019). Learning to infer program sketches. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, California.
- Bastani, O., Pu, Y., Solar-Lezama, A. (2018). Verifiable reinforcement learning via policy extraction. Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems (NeurIPS), Montréal, Canada.
Media
- March 24, 2020: CSAIL News, Armando Solar-Lezama wins NSF Expeditions Grant.
- June 14, 2019: MIT News, Toward artificial intelligence that learns to write code.
- May 25, 2017: MIT News, Armando Solar-Lezama: Academic success despite an inauspicious start.
- Nov. 7, 2016: MIT News, Faster programs, easier programming.