Normalizing Flows with Iterative Denoising · AI HOT

Apple Machine Learning Research（RSS）

精选61

Normalizing Flows with Iterative Denoising

2026-05-06 08:00·40天前

精选理由

Normalizing Flows 这个老方法被苹果玩出新花样，iTARFlow 在训练上保留端到端似然，采样却自回归，给做生成模型的人提供了扩散模型之外的第二个靠谱选择。

AI 摘要

研究团队在归一化流（NFs）生成模型领域取得新进展，提出了迭代TARFlow（iTARFlow）。该方法在训练阶段保持完全端到端的基于似然的目标，采样时则采用自回归生成方式。iTARFlow延续了TARFlow在图像建模任务上的优势，使其成为扩散模型等方法的可行替代方案，进一步提升了归一化流生成模型的性能表现。

原文 · 未翻译

Normalizing Flows with Iterative Denoising

Normalizing Flows with Iterative Denoising

AuthorsTianrong Chen, Jiatao Gu, David Berthelot, Joshua Susskind, Shuangfei Zhai

View publication

View source code (GitHub)

Copy Bibtex

Normalizing Flows (NFs) are a classical family of likelihood-based methods that have received revived attention. Recent efforts such as TARFlow have shown that NFs are capable of achieving promising performance on image modeling tasks, making them viable alternatives to other methods such as diffusion models. In this work, we further advance the state of Normalizing Flow generative models by introducing iterative TARFlow (iTARFlow). Unlike diffusion models, iTARFlow maintains a fully end-to-end, likelihood-based objective during training. During sampling, it performs autoregressive generation followed by an iterative denoising procedure inspired by diffusion-style methods. Through extensive experiments, we show that iTARFlow achieves competitive performance across ImageNet resolutions of 64, 128, and 256 pixels, demonstrating its potential as a strong generative model and advancing the frontier of Normalizing Flows. In addition, we analyze the characteristic artifacts produced by iTARFlow, offering insights that may shed light on future improvements. Code is available at https://github.com/apple/ml-itarflow.

Related readings and updates.

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

June 30, 2025research area Computer Vision, research area Methods and Algorithmsconference NeurIPS

We present STARFlow, a scalable generative model based on normalizing flows that achieves strong performance in high-resolution image synthesis. The core of STARFlow is Transformer Autoregressive Flow (TARFlow), which combines the expressive power of normalizing flows with the structured modeling capabilities of Autoregressive Transformers. We first establish the theoretical universality of TARFlow for modeling continuous distributions. Building…

Normalizing Flows are Capable Generative Models

Normalizing Flows are Capable Generative Models

June 27, 2025research area Computer Vision, research area Methods and Algorithmsconference ICML

Normalizing Flows (NFs) are likelihood-based models for continuous inputs. They have demonstrated promising results on both density estimation and generative modeling tasks, but have received relatively little attention in recent years. In this work, we demonstrate that NFs are more powerful than previously believed. We present TarFlow: a simple and scalable architecture that enables highly performant NF models. TarFlow can be thought of as a…

Discover opportunities in Machine Learning.

Our research in machine learning breaks new ground every day.

Work with us

图像生成论文/研究

Apple Machine Learning Research（RSS）

精选61

Normalizing Flows with Iterative Denoising

2026-05-06 08:00·40天前

精选理由

Normalizing Flows 这个老方法被苹果玩出新花样，iTARFlow 在训练上保留端到端似然，采样却自回归，给做生成模型的人提供了扩散模型之外的第二个靠谱选择。

AI 摘要

研究团队在归一化流（NFs）生成模型领域取得新进展，提出了迭代TARFlow（iTARFlow）。该方法在训练阶段保持完全端到端的基于似然的目标，采样时则采用自回归生成方式。iTARFlow延续了TARFlow在图像建模任务上的优势，使其成为扩散模型等方法的可行替代方案，进一步提升了归一化流生成模型的性能表现。

原文 · 保持原样，未翻译

Normalizing Flows with Iterative Denoising

Normalizing Flows with Iterative Denoising

AuthorsTianrong Chen, Jiatao Gu, David Berthelot, Joshua Susskind, Shuangfei Zhai

View publication

View source code (GitHub)

Copy Bibtex

Normalizing Flows (NFs) are a classical family of likelihood-based methods that have received revived attention. Recent efforts such as TARFlow have shown that NFs are capable of achieving promising performance on image modeling tasks, making them viable alternatives to other methods such as diffusion models. In this work, we further advance the state of Normalizing Flow generative models by introducing iterative TARFlow (iTARFlow). Unlike diffusion models, iTARFlow maintains a fully end-to-end, likelihood-based objective during training. During sampling, it performs autoregressive generation followed by an iterative denoising procedure inspired by diffusion-style methods. Through extensive experiments, we show that iTARFlow achieves competitive performance across ImageNet resolutions of 64, 128, and 256 pixels, demonstrating its potential as a strong generative model and advancing the frontier of Normalizing Flows. In addition, we analyze the characteristic artifacts produced by iTARFlow, offering insights that may shed light on future improvements. Code is available at https://github.com/apple/ml-itarflow.

Related readings and updates.

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

June 30, 2025research area Computer Vision, research area Methods and Algorithmsconference NeurIPS

We present STARFlow, a scalable generative model based on normalizing flows that achieves strong performance in high-resolution image synthesis. The core of STARFlow is Transformer Autoregressive Flow (TARFlow), which combines the expressive power of normalizing flows with the structured modeling capabilities of Autoregressive Transformers. We first establish the theoretical universality of TARFlow for modeling continuous distributions. Building…