Gregory Wornell

Gregory Wornell is the Sumitomo Electric Industries Professor in Engineering in MIT’s Department of Electrical Engineering and Computer Science (EECS). He is also affiliated with the Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Institute for Data, Systems, and Society (IDSS). Wornell heads the Signals, Information, and Algorithms Laboratory within the Research Laboratory of Electronics (RLE). His research interests span signal processing, information theory, statistical inference, and information security, and include architectures for sensing, learning, computing, communication, and storage; systems for computational imaging, vision, and perception; and aspects of neuroscience. Wornell earned a BASc from the University of British Columbia, and an SM and PhD from MIT.

Selected Publications

• Shah, A., Shen, M., Ryu, J., Das, S., Sattigeri, P., Bu, Y., & Wornell, G. (2024). Group fairness with uncertainty in sensitive attributes. In Proceedings of the 2024 IEEE International Symposium on Information Theory (ISIT 2024), July 7-12, Athens, Greece.
• Shen, M., Das, S., Greenewald, K., Sattigeri, P., Wornell, G.W. & Ghosh, S. (2024). Thermometer: Towards Universal Calibration for Large Language Models. In Proceedings of Machine Learning Research 235:44687-44711
• Shen, M., Sattigeri, P., Ghosh, S., Das, S., Bu, Y., Wornell, G. (2023). Post-hoc Uncertainty Learning using a Dirichlet Meta-Model. Association for the Advancement of Artificial Intelligence (AAAI).

Media

• July 31, 2024: MIT News, Method prevents an AI model from being overconfident about wrong answers
• February 13, 2023: MIT News, Efficient technique improves machine-learning models’ reliability
• July 20, 2022: MIT News, A technique to improve both fairness and accuracy in artificial intelligence