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.
arXiv preprint arXiv:2207.07732 (2022)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A two-stage framework enables multimodal LLMs to learn shared latent representations from pairwise modality data and achieve cross-modal generation when incorporating new modalities.
Derives optimality constraints for nonnegative joint dictionary learning that explain observed SAE behaviors such as feature splitting, absorption, and dense antipodal features.
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.
-
Multimodal LLMs under Pairwise Modalities
A two-stage framework enables multimodal LLMs to learn shared latent representations from pairwise modality data and achieve cross-modal generation when incorporating new modalities.
-
How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations
Derives optimality constraints for nonnegative joint dictionary learning that explain observed SAE behaviors such as feature splitting, absorption, and dense antipodal features.