arXiv Machine Learning September 11, 2026 By Qi Chen, Jierui Zhu, Florian Shkurti

Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis

Read the original on arXiv Machine Learning →

arXiv:2506. 00849v2 Announce Type: replace Abstract: Despite the empirical success of Diffusion Models (DMs) and Variational Autoencoders (VAEs), their generalization performance remains theoretically underexplored, especially lacking a full consideration of the shared encoder-generator structure.

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

Jun 4

Geometry-Preserving Encoder/Decoder in Latent Generative Models

arXiv:2501. 09876v3 Announce Type: replace-cross Abstract: Generative modeling aims to generate new data samples that resemble a given dataset.

By Wonjun Lee, Riley C. W. O'Neill, Dongmian Zou, Jeff Calder, Gilad Lerman

diffusion benchmarks

arXiv Machine Learning

Aug 6

Regularization can make diffusion models more efficient

arXiv:2502. 09151v3 Announce Type: replace Abstract: Diffusion models are one of the key architectures of generative AI.

By Mahsa Taheri, Johannes Lederer

diffusion efficiency

arXiv AI

Jul 24

From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime

arXiv:2607. 20540v1 Announce Type: cross Abstract: How should a diffusion model decide which noise levels to train on, and how much?

By Luca Ambrogioni, Giulio Franzese, Alberto Foresti, Gabriel Raya, Bac Nguyen, Georgios Batzolis, Yuhta Takida, Naoki Murata, Chieh-Hsin Lai, Yuki Mitsufuji

diffusion

arXiv Machine Learning

Jun 10

The Emergence of Reproducibility and Generalizability in Diffusion Models

arXiv:2310. 05264v5 Announce Type: replace Abstract: In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs.

By Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Peng Wang, Liyue Shen, Qing Qu

diffusion fine-tuning safety

arXiv Machine Learning

Jul 22

ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling

arXiv:2607. 19332v1 Announce Type: new Abstract: Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching.

By Chirag Vashist, Ke Li

llms diffusion safety

arXiv Machine Learning

Jun 9

Self-Consistent Generative Paths via Admissible Random Variational Transport

arXiv:2606. 08953v1 Announce Type: new Abstract: Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map.

By Lei Luo, Yingzhen Zhang, Jian Yang

diffusion efficiency safety

One email a morning, machine-written

Related stories

Geometry-Preserving Encoder/Decoder in Latent Generative Models

Regularization can make diffusion models more efficient

From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime

The Emergence of Reproducibility and Generalizability in Diffusion Models

ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling

Self-Consistent Generative Paths via Admissible Random Variational Transport