FFJORD: Free-form continuous dynamics for scalable reversible generative models

An invertible generative model for forward and inverse problems

arXiv:2509. 03910v2 Announce Type: replace-cross Abstract: We formulate inverse problems in a Bayesian framework and aim to train an invertible generative model that is capable of simulation (i.

Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation

arXiv:2511. 09002v3 Announce Type: replace-cross Abstract: Self-consuming generative models have received significant attention over the last few years.

On the quantitative analysis of decoder-based generative models

On Forgetting and Stability of Score-based Generative models

arXiv:2601. 21868v2 Announce Type: replace-cross Abstract: Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning.

Volterra Generative Models

arXiv:2606. 18071v1 Announce Type: cross Abstract: Score-based diffusion models typically use Brownian perturbations, which provide tractable reverse-time dynamics but impose memoryless noising.

Glow: Better reversible generative models

We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It extends previous work on reversible generative models and simplifies the architecture.