arXiv Machine Learning July 28, 2026 By Ye Shi

Soft-Constrained Optimization of Latent Space in Variational Autoencoders

Read the original on arXiv Machine Learning →

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.

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.

diffusion

arXiv Machine Learning

Jul 28

A Multi-stage Constrained Optimization Framework for Data-driven Problems

arXiv:2607. 23480v1 Announce Type: new Abstract: Variational autoencoders (VAEs) transform high-dimensional, often noisy data into a compact latent representation, making downstream optimization more tractable.

By Ye Shi

diffusion safety

arXiv Machine Learning

Jul 3

eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions

arXiv:2607. 01275v1 Announce Type: cross Abstract: Variational Autoencoders (VAEs) commonly assume a standard isotropic Gaussian prior over the latent space, an assumption that often fails to capture the true distribution of latent representations for complex datasets.

By Qijun Chen, Shaofan Li

diffusion benchmarks

arXiv Machine Learning

Jun 9

Disentanglement with Holographic Reduced Representations

arXiv:2606. 09725v1 Announce Type: new Abstract: Disentanglement, the separation of factors of variation in data using neural networks, remains a long-standing challenge in machine learning.

By Jhonny J. Velasquez Olivera, Christo K. Thomas, Walid Saad

safety

arXiv Machine Learning

Jul 8

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

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.

By Girum Demisse

benchmarks

arXiv Machine Learning

Jun 17

Variational autoencoders with latent high-dimensional steady geometric flows for dynamics

arXiv:2410. 10137v5 Announce Type: replace Abstract: We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds.

By Andrew Gracyk

diffusion

arXiv AI

Sep 2

Superposed Latent Autoencoder

The paper introduces the Superposed Latent Autoencoder (SLAE), a method that stores multiple wide latent representations together by superposing them into a single memory tensor using learned codes and randomized keys. SLAE eliminates the need for tight dimensional bottlenecks, achieving up to 56% lower reconstruction error on datasets such as CIFAR-10/100 and SVHN while maintaining the same storage budget. The approach also boosts downstream classification performance by up to 16.79 percentage points, demonstrating that wide representations can be effectively compressed through structured interference rather than dimensional reduction.

By Quanling Zhao, Jiaying Yang, Tianqi Zhang, Ziyang Hao, Fatemeh Asgarinejad, Flavio Ponzina, Tajana Rosing

One email a morning, machine-written

Related stories

A Multi-stage Constrained Optimization Framework for Data-driven Problems

eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions

Disentanglement with Holographic Reduced Representations

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

Variational autoencoders with latent high-dimensional steady geometric flows for dynamics

Superposed Latent Autoencoder