Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification

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.