Causal Representation Learning

OCIS: BISCUIT - Causal Representation Learning from Binary Interactions

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

CARE: BISCUIT - Causal Representation Learning from Binary Interactions

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

On Practical Challenges of Scaling Causal Representation Learning

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

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.

UAI Spotlight Talk: BISCUIT - Causal Representation Learning from Binary Interactions

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

BISCUIT - Causal Representation Learning from Binary Interactions

Causal Representation Learning meets Embodied AI

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.

KAUST Rising Stars in AI: Causal Representation Learning

I was invited to the Rising Stars in AI Symposium to give a talk on our work in Causal Representation Learning.