登入
洞見 - Causal Representation Learning
Causal Diffusion Autoencoders: A Framework for Counterfactual Image Generation using Diffusion Probabilistic Models
CausalDiffAE, a diffusion-based framework for learning disentangled causal representations and enabling controllable counterfactual generation.
Estimating Domain Counterfactuals for Invertible Latent Causal Models without Recovering the Full Causal Structure
It is possible to estimate domain counterfactuals without recovering the full latent causal structure by leveraging the invertibility and sparsity of the causal mechanisms.
Recovering Hidden Causal Variables and Their Relationships from Multiple Distributions: A General Nonparametric Framework
Under sparsity constraints on the recovered latent graph and sufficient changes in the causal influences, the hidden causal variables and their causal relations can be recovered up to specific, relatively minor indeterminacies.
Towards Reusability and Compositionality of Causal Representations in CRL
Adapting causal representations for new environments using DECAF framework.
