causal-representation-learning

This paper introduces concept modulation models (CMMs), a unified framework for identifiability and extrapolation in conditional generative models. It shows that feature agreement on observed attributes induces constraints through attribute potentials, enabling algebraic extrapolation criteria that recover and generalize existing results.

This paper critiques the 'Proxy Presumption' in NLP, where geometric embedding properties are incorrectly equated with social constructs. It introduces the Construct Validity Protocol and Counterfactual Neutralization methods to ensure rigorous validation of social measures derived from semantic embeddings.

This paper introduces MOSAIC, a method for module discovery in scientific time series that combines causal representation learning with sparse additive identifiable causal learning. It aims to recover interpretable latent variables and their associated observations without post-hoc alignment, validated on domains like molecular dynamics and climate data.