Ben Glocker

Decoupled Classifier-Free Guidance for Counterfactual Diffusion Models

Counterfactual Identifiability via Dynamic Optimal Transport

Rethinking Fair Representation Learning for Performance-Sensitive Tasks

Diffusion Counterfactual Generation with Semantic Abduction

Subgroups Matter for Robust Bias Mitigation

Identifiable Object Representations under Spatial Ambiguities

Continuous Bayesian Model Selection for Multivariate Causal Discovery

Multi-view Object-Centric Learning with Identifiable Representations