Causal representation learning seeks to extract high-level latent factors from low-level
sensory data. Most existing methods rely on observational data and structural assumptions …

Temporal data, representing chronological observations of complex systems, has always
been a typical data structure that can be widely generated by many domains, such as …

We study causal representation learning, the task of inferring latent causal variables and
their causal relations from high-dimensional functions (“mixtures”) of the variables. Prior …

Multi-source domain adaptation (MSDA) methods aim to transfer knowledge from multiple
labeled source domains to an unlabeled target domain. Although current methods achieve …

For safe motion planning in real-world autonomous vehicles require behavior prediction
models that are reliable and robust to distribution shifts. The recent studies suggest that the …

Recently in the field of unsupervised representation learning, strong identifiability results for
disentanglement of causally-related latent variables have been established by exploiting …

Causal representation learning promises to extend causal models to hidden causal
variables from raw entangled measurements. However, most progress has focused on …

Identifying the causal variables of an environment and how to intervene on them is of core
value in applications such as robotics and embodied AI. While an agent can commonly …

This work introduces a novel principle for disentanglement we call mechanism sparsity
regularization, which applies when the latent factors of interest depend sparsely on …

Nonlinear independent component analysis (ICA) aims to uncover the true latent sources
from their observable nonlinear mixtures. Despite its significance, the identifiability of …