Phillip Isola is an assistant professor in MIT’s Department of Electrical Engineering and Computer Science and an investigator in the Computer Science and Artificial Intelligence Laboratory. His work focuses on why we represent the world the way we do, and how we can replicate these abilities in machines. Before coming to MIT, he was a visiting research scientist at OpenAI. He earned a PhD in brain and cognitive sciences at MIT and spent two years as a postdoc at the University of California, Berkeley.
- Tian, Y., Krishnan, D., Isola, P. (2020). Contrastive Representation Distillation. The International Conference on Learning Representations.
- Jahanian, A., Chai, L., Isola, P. (2020). On the “steerability” of generative adversarial networks. The International Conference on Learning Representations (ICLR).
- Pathak, D., Lu, C., Darrell, T., Isola, P., Efros, A. A. (2019). Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity. Thirty-third Conference on Neural Information Processing Systems (NeurIPS).
- Yen-Chen, L., Bauza, M., Isola, P. (2019). Experience-embedded Visual Foresight. 3rd Annual Conference on Robot Learning (CoRL).
- November 1, 2019: MIT News, What makes an image memorable? Ask a computer.
- October 21, 2019: MIT News, Pushy robots learn the fundamentals of object manipulation.
- May 30, 2019: MIT News, Q&A: Phillip Isola on the art and science of generative models.
- June 13, 2016: MIT News, Artificial intelligence produces realistic sounds that fool humans.