I gave an overview on recent advances in causal representation learning and possible relations to causal incentives analysis in AGI safety at the Causal Incentive Working Group.
I gave an invited talk on our vision for causal representation learning from temporal observations at the First Workshop on Causal Representation Learning at UAI 2022.
We derive a minimal bound of experiments that guarantee identifiability of causal variables, opening up new opportunities for using intervention design for causal representation learning.
We present CITRIS, a causal representation learning algorithm for multidimensional causal factors identified from videos with interventions. Published at ICML 2022 (**Spotlight**).
We identify causal variables and their graphs from pairs of high-dimensional observations between which single interventions have been performed. Published at NeurIPS 2022.