Mechanistic independence criteria yield identifiability of latent subspaces under nonlinear mixing by focusing on action-based independence rather than latent distributions, with a hierarchy and graph-theoretic view of subspaces.
Identifia- bility results for multimodal contrastive learning.arXiv preprint arXiv:2303.09166
5 Pith papers cite this work, alongside 4 external citations. Polarity classification is still indexing.
5
Pith papers citing it
4
external citations · external index
representative citing papers
Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.
Self-supervised learning can be understood as latent distribution matching, and under a Gaussian predictive model this yields identifiable representations up to affine transformations.
Using the mosaic controlled dataset framework, experiments show scene complexity dominates over concept imbalance in diffusion model failures for multi-object generation, with counting especially hard in low-data regimes and compositional generalization collapsing under held-out combinations.
MoVA introduces modular asymmetric dual projections to handle temporal misalignment and semantic asymmetry in long video-text alignment.
citing papers explorer
-
Mechanistic Independence: A Principle for Identifiable Disentangled Representations
Mechanistic independence criteria yield identifiability of latent subspaces under nonlinear mixing by focusing on action-based independence rather than latent distributions, with a hierarchy and graph-theoretic view of subspaces.
-
Unsupervised Causal Abstractions Discovery
Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.
-
Understanding Self-Supervised Learning via Latent Distribution Matching
Self-supervised learning can be understood as latent distribution matching, and under a Gaussian predictive model this yields identifiable representations up to affine transformations.
-
When Do Diffusion Models learn to Generate Multiple Objects?
Using the mosaic controlled dataset framework, experiments show scene complexity dominates over concept imbalance in diffusion model failures for multi-object generation, with counting especially hard in low-data regimes and compositional generalization collapsing under held-out combinations.
-
MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
MoVA introduces modular asymmetric dual projections to handle temporal misalignment and semantic asymmetry in long video-text alignment.