Causal Representation Learning

Language Agents Meet Causality - Bridging LLMs and Causal World Models

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

Towards the Reusability and Compositionality of Causal Representations

We introduce DECAF, a framework that is a first step towards adapting and composing causal representations.

Hierarchical Causal Representation Learning

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 - Causal Representation Learning from Binary Interactions

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**).

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems

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.

Intervention Design for Causal Representation Learning

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.

CITRIS - Causal Identifiability from Temporal Intervened Sequences

We present CITRIS, a causal representation learning algorithm for multidimensional causal factors identified from videos with interventions. Published at ICML 2022 (**Spotlight**).

Weakly supervised causal representation learning

We identify causal variables and their graphs from pairs of high-dimensional observations between which single interventions have been performed. Published at NeurIPS 2022.