arXiv Machine Learning July 8, 2026 By Girum Demisse

$\mathbf{\lambda}$-VAE: Variance Equalization for Posterior Collapse

Read the original on arXiv Machine Learning →

arXiv:2607. 05531v1 Announce Type: new Abstract: Variational Autoencoders (VAEs) frequently suffer from posterior collapse, a failure mode in which the approximate posterior converges to the prior, rendering the latent code uninformative.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

benchmarks

arXiv AI

Jun 24

A Simplex Witness Certificate and Escape Force for Constant Collapse in Variational Autoencoders

arXiv:2605. 18224v4 Announce Type: replace-cross Abstract: We study exact constant collapse in variational autoencoders: the deterministic encoder mean becomes independent of the input.

By Zegu Zhang, Jian Zhang

safety

arXiv AI

Jul 3

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

arXiv:2607. 01799v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) decompose internal activations of neural networks into sparse linear combinations of learned features by fitting an overcomplete dictionary $\mathbf{W}\in\mathbb{R}^{m\times n}$ with $m<n$, and inferring a sparse code $\mathbf{x}\in\mathbb{R}^n$ from $\mathbf{h}\approx\mathbf{W}\mathbf{x}$.

By Rodrigo Mendoza-Smith

llms safety

arXiv Machine Learning

Jul 28

Soft-Constrained Optimization of Latent Space in Variational Autoencoders

arXiv:2607. 23751v1 Announce Type: new Abstract: The usefulness of a variational autoencoder (VAE) depends on two properties of its latent space that are hard to obtain together: high encoding capacity in the individual latent variables, and a low-dimensional, disentangled organization of those variables.

By Ye Shi

diffusion

arXiv Machine Learning

Jul 21

Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression?

arXiv:2607. 17425v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) compress model activations into sparse codes, but equal reconstruction error and sparsity can preserve different linearly decodable signals.

By Aniket Deshpande

llms efficiency benchmarks

arXiv Machine Learning

Jun 25

An Analysis of Posterior Collapse, Parameterization and Initialization in Variational Deep Gaussian Processes

arXiv:2606. 25882v1 Announce Type: new Abstract: DGPs are probabilistic models with remarkable prediction performance that concatenate GPs across several layers.

By Francisco Javier S\'aez-Maldonado, Juan Maro\~nas, Daniel Hern\'andez-Lobato

arXiv Machine Learning

Aug 27

Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching

arXiv:2608. 25138v1 Announce Type: new Abstract: Stochastic masking, cropping, or modality removal makes deterministic reconstruction an incomplete target: one observation can admit many clean completions.

By Jiarui Cao

diffusion multimodal benchmarks

One email a morning, machine-written

Related stories

A Simplex Witness Certificate and Escape Force for Constant Collapse in Variational Autoencoders

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

Soft-Constrained Optimization of Latent Space in Variational Autoencoders

Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression?

An Analysis of Posterior Collapse, Parameterization and Initialization in Variational Deep Gaussian Processes

Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching