OCIS: BISCUIT - Causal Representation Learning from Binary Interactions

Abstract

Together with Sara Magliacane, I was invited to give a talk on our recent work BISCUIT. Sara gave an introduction on Causal Representation Learning for Temporal Sequences. In the second part, I gave a detailed overview of BISCUIT, including the the theory, the architecture, and our experimental results. For more details, check out our paper and project page.