arXiv Machine Learning August 3, 2026 By S\'ebastien Lachapelle, Pau Rodr\'iguez L\'opez, Yash Sharma, Katie Everett, R\'emi Le Priol, Alexandre Lacoste, Simon Lacoste-Julien

Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies

Read the original on arXiv Machine Learning →

arXiv:2401. 04890v2 Announce Type: replace-cross Abstract: This work introduces a novel principle for disentanglement we call mechanism sparsity regularization, which applies when the latent factors of interest depend sparsely on observed auxiliary variables and/or past latent factors.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

efficiency

arXiv Machine Learning

Jun 9

Causal Representation Learning from Network Data

arXiv:2509. 01916v2 Announce Type: replace Abstract: Causal disentanglement from soft interventions is identifiable under the assumptions of linear interventional faithfulness and availability of both observational and interventional data.

By Jifan Zhang, Michelle M. Li, Elena Zheleva

arXiv Machine Learning

1d ago

The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning

arXiv:2608. 16245v1 Announce Type: new Abstract: Disentangled representation learning seeks latent representations whose indicidual dimensions each align with a distinct covariate.

By Ma{\l}gorzata {\L}az\k{e}cka, Ewa Szczurek

diffusion safety

arXiv AI

Jun 17

FoundCause: Causal Discovery with Latent Confounders from Observational Data

arXiv:2606. 17516v1 Announce Type: cross Abstract: Causal discovery from observational data remains challenging due to the need to recover directed structure and latent confounding without interventions.

By Patrick Bl\"obaum, Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan

llms

arXiv Machine Learning

Aug 12

Causal Variational Deep Embedding: A Family of Interventional Generators for Confounded Images

arXiv:2606. 21806v2 Announce Type: replace Abstract: Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains.

By Jingyuan Chen, Kangrui Ruan, Junzhe Zhang

rag benchmarks

arXiv AI

Jul 24

Constrained latent state modeling: A unifying perspective on representation learning under competing constraints

arXiv:2605. 15995v2 Announce Type: replace-cross Abstract: Learning latent representations from complex data is central to modern machine learning, spanning temporal, multimodal, and partially observed systems.

By Gwenol\'e Quellec

multimodal benchmarks

arXiv AI

Jul 10

XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision

arXiv:2601. 21688v2 Announce Type: replace-cross Abstract: Disentangled representation learning aims to map independent factors of variation to independent representation components.

By Alexandre Myara, Nicolas Bourriez, Thomas Boyer, Thomas Lemercier, Ihab Bendidi, Auguste Genovesio

benchmarks safety

Related stories

Causal Representation Learning from Network Data

The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning

FoundCause: Causal Discovery with Latent Confounders from Observational Data

Causal Variational Deep Embedding: A Family of Interventional Generators for Confounded Images

Constrained latent state modeling: A unifying perspective on representation learning under competing constraints

XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision