按年被提到
20252025 · 2 次2026
视觉、语音与图像生成›扩散模型·arXiv:2510.21890 · cs.LG

The Principles of Diffusion Models

Chieh-Hsin Lai, Yang Song, Dongjun Kim, Yuki Mitsufuji, Stefano Ermon · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-10-29 · 最近 2025-11-09
2不同的人
2活跃月份
2讨论串
—被引(OpenAlex)
arXiv 摘要(候选层不写导读)

This book presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematical ideas. Diffusion modeling starts by defining a forward process that gradually corrupts data into noise, linking the data distribution to a simple prior through a continuum of intermediate distributions. The goal is to learn a reverse process that transforms noise back into data while recovering the same intermediates. We describe three complementary views. The variational view, inspired by variational autoencoders, sees diffusion as learning to remove noise step by step. The score-based view, rooted in energy-based modeling, learns the gradient of the evolving data distribution, indicating how to nudge samples toward more likely regions. The flow-based view, related to normalizing flows, treats generation as following a smooth path that moves samples from noise to data under a learned velocity field. These perspectives share a common backbone: a time-dependent velocity field whose flow transports a simple prior to the data. Sampling then amounts to solving a differential equation that evolves noise into data along a continuous trajectory. On this foundation, the book discusses guidance for controllable generation, efficient numerical solvers, and diffusion-motivated flow-map models that learn direct mappings between arbitrary times. It provides a conceptual and mathematically grounded understanding of diffusion models for readers with basic deep-learning knowledge. Supplementary materials for the book are available at the book website: https://the-principles-of-diffusion-models.github.io/

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

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论smokel · 2025-11

“If you're more into videos, be sure to check out Stefano Ermon's CS236 Deep Generative Models [1]. All lectures are available on YouTube [2]. [1] https://deepgenerativemodels.github.io/ [2] https://m.youtube.com/playlist?list=PLoROMvodv4rPOWA-omMM6STXaWW4FvJT8”

The Principles of Diffusion Models原评论 ↗
讨论串评论leptons · 2025-11

“Reading this reinforces that a lot of what makes up current "AI" is brute forcing and not actually intelligent or thoughtful. Although I suppose our meat-minds could also be brute-forcing everything throughout our entire lives, and consciousness is like a chat prompt sitting on top of the machinery of the mind. But artificial intelligence will always be j…”

The Principles of Diffusion Models原评论 ↗
讨论串评论gdmaher · 2025-11

“Cool (but long) text. I wanted an overview so I used claude to make a chapter-by-chapter summary, sharing in case anyone else finds it useful https://github.com/gmaher/diffusion_principles_summary”

The Principles of Diffusion Models原评论 ↗
被提交为 story · 2 次