Test-Time Debiasing of Vision-Language Embeddings
Walter Gerych
Walter Gerych is a postdoctoral associate at MIT CSAIL. He earned his Ph.D. and M.S. in Data Science from Worcester polytechnic Institute . Walter’s research focuses primarily on designing ML and deep learning systems that are robust to labeling and sampling errors and biases. His primary application areas revolve around mobile sensor time series for human activity recognition and mobile healthcare.
Haoran Zhang
Haoran is a fourth year PhD student in EECS at MIT. He is generally interested in building robust machine learning models that maintain their performance and fairness across out-of-distribution environments, as well as applying such models to the healthcare setting. Haoran previously received his M.Sc. at the University of Toronto under the co-supervision of Dr. Marzyeh Ghassemi and Dr. Quaid Morris, and his B.Eng. from McMaster University.
Kimia Hamidieh
Kimia is a PhD student at MIT EECS. Her research focuses on understanding how self-supervised pre-training strategies represent data to build models that generalize well out-of-distribution, as well as developing post-training strategies that ensure safety of models. She previously received her MSc at the University of Toronto and her BSc from Sharif University of Technology.
Eileen Pan
Eileen Pan is a 2nd-year EECS PhD student at MIT co-advised by Marzyeh Ghassemi and Ashia Wilson. Her research focuses on developing scalable ways to audit and mitigate bias in deep learning models, with applications to healthcare. She also completed her BS in Computation and Cognition at MIT as a Questbridge Scholar. Her work is supported by the Jameel Clinic Fellowship and NSF Graduate Research Fellowship.