Causal Representation Learning

We combine Causal Representation Learning with LLMs for reasoning about world models.

I presented our work BISCUIT, on making CRL viable on realistic, temporal interactive environments.

I presented our work BISCUIT, on making CRL viable on realistic, temporal interactive environments.

I presented an overview of our efforts on scaling Causal Representation Learning towards real-world settings.

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.

I presented our UAI spotlight paper on learning causal representation learning from low-level actions.

Causal Representation Learning meets Embodied AI

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.