Causal Representation Learning
We combine Causal Representation Learning with LLMs for reasoning about world models.
We introduce DECAF, a framework that is a first step towards adapting and composing causal representations.
We introduce the problem of hierarchical causal representation learning and show how our method, HERCULES, can generalize across environments with much fewer fine-grained interventions.
BISCUIT identifies causal variables from videos using binary interactions between an external system (e.g. robot) and the causal variables. Published at UAI 2023 (**Spotlight**).
We present iCITRIS, a causal representation learning method that can identify causal variables with instantaneous effects and their graph from temporal sequences. Published at ICLR 2023.
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.