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.
PDE-Refiner is an iterative refinement process that enables neural operator training for accurate and stable predictions over long time horizons. Published at NeurIPS 2023 (**Spotlight**).
This paper introduces several advancements for continuous and distributed object-centric representations, scaling them from simple toy to real-world data.