We have 5 of 24 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
SplitJEPA is introduced, a JEPA that jointly recovers the latent state and its invariant and variant organization directly in representation space, without any reconstruction, and extends reconstruction-free latent recovery to invariant-variant block identification.
DSReg (Dependency-Sparsity Regularization) recovers individual world latents up to signed permutation, without reconstruction or a decoder, without reconstruction or a decoder, and establishes the first fully identifiable JEPA that recovers every world latent.
This work characterize structural misspecification as a perturbed factor analysis problem, and establishes subspace identifiability under spectral separation and controlled perturbation, followed by component-wise identifiability under structural sparsity.
A condition called the cross-Hessian Rank Constraint (HRC), which serves as a primitive rank-based tool for nonlinear latent causal discovery, shows that a rank-based property arises from the cross-Hessian of the observed-data log-density in the nonlinear case, revealing information about the latent variables.
Compression is fundamental to intelligence. A model that can represent its training data as a short code has discovered regularities that enable generalization. Large neural networks may learn functions far simpler than their parameter counts suggest, but it is challenging to construct codes that realize this simplicit...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
