arXiv cs.AI· Tianhua Chen·· 10 小时前AI 评分24
生成模型如何生成:生成式 AI 全景简明指南
How Generative Models Generate: A Concise Guide to the Generative AI Landscape
AI 导读
一篇 arXiv 技术指南以“生成”为中心,将生成式 AI 方法归纳为三条反复出现的生成路径:直接变换或解码、顺序条件构建、迭代更新或传输。文章按关键组件、学习目标和采样过程介绍代表性方法,并考察不同架构与生成机制之间的重叠与组合,帮助读者在紧凑的概念框架内理解陌生方法、识别模型间的联系。
正文 · 原文
Abstract:The rapidly expanding generative AI landscape brings together methods that differ in architecture, learning objective, mathematical representation and sampling procedure. A concise, selectively organised technical guide can provide an accessible starting point for developing a coherent understanding of this increasingly complex landscape. This article takes a generation-centred approach, connecting how models produce new observations with the modelling and learning principles that make generation possible. We develop a two-level perspective: first, distinguishing three recurring generation routes-direct transformation or decoding, sequential conditional construction, and iterative updating or transport; and second, examining the modelling and learning principles underlying these routes. Representative approaches are introduced through their key components, learning objectives and sampling procedures. We then examine their broader connections, including how different architectures and generation mechanisms can overlap or be combined. By bringing together essential technical explanations within a compact conceptual framework, the article aims to help readers develop a working understanding of unfamiliar approaches, recognise connections among models they have encountered, and navigate different approaches within the broader generative AI landscape.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.24728 [cs.LG] |
| (or arXiv:2611.24728v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.24728 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tianhua Chen [view email]
[v1]
Wed, 18 Nov 2026 16:45:19 UTC (28 KB)
来源:arXiv cs.AI · arxiv.org