按年被提到
20252025 · 3 次2026
视觉、语音与图像生成›图像与视频生成·arXiv:2506.06276 · cs.CV

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

Jiatao Gu, Tianrong Chen, David Berthelot, Huangjie Zheng, Yuyang Wang, Ruixiang Zhang, Laurent Dinh, Miguel Angel Bautista, Josh Susskind, Shuangfei Zhai · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-06-27 · 最近 2025-08-08
2不同的人
2活跃月份
3讨论串
3被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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 on this foundation, we introduce several key architectural and algorithmic innovations to significantly enhance scalability: (1) a deep-shallow design, wherein a deep Transformer block captures most of the model representational capacity, complemented by a few shallow Transformer blocks that are computationally efficient yet substantially beneficial; (2) modeling in the latent space of pretrained autoencoders, which proves more effective than direct pixel-level modeling; and (3) a novel guidance algorithm that significantly boosts sample quality. Crucially, our model remains an end-to-end normalizing flow, enabling exact maximum likelihood training in continuous spaces without discretization. STARFlow achieves competitive performance in both class-conditional and text-conditional image generation tasks, approaching state-of-the-art diffusion models in sample quality. To our knowledge, this work is the first successful demonstration of normalizing flows operating effectively at this scale and resolution.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论yorwba · 2025-06

“They took a simple technique (normalizing flows), instantiated its basic building blocks with the most general neural network architecture known to work well (transformer blocks), and trained models of different sizes on various datasets to see whether it scales. Looks very bitter-lesson-pilled to me. That they didn't scale beyond AFHQ (high-quality anim…”

Apple Research unearthed forgotten AI technique and using it to generate images原评论 ↗
评论yorwba · 2025-06

“Figure 10 in https://arxiv.org/pdf/2506.06276 has a speed comparison. You need fairly large batch sizes for this method to come out ahead. The issue is that the architecture is very sequential, so you need to be generating several images at the same time to make good use of GPU parallelism.”

Normalizing Flows Are Capable Generative Models原评论 ↗
评论godelski · 2025-08

“> which is what you get when you look at non-LLM alternatives to General Intelligence. I disagree with this. There are a good ideas that are worth pursuit. I'll give you that few, if any, have been shown to work at scale but I'd say that's a self-fulfilling prophecy. If your bar is that they have to be proven at scale then your bar is that to get investme…”

GPT-5: Key characteristics, pricing and system card原评论 ↗