将生成模型统一视为概率变换函数，揭示其本质共性。
Deep generative models as the probability transformation functions
- 把各类生成模型看作将简单分布变换成复杂数据分布的变换函数。
- 所有主流生成模型（如扩散、流匹配、GAN等）都遵循同一核心机制。
- 为跨模型方法迁移和通用理论发展提供新思路，适合研究者参考。
本文提出一种统一的理论视角，将深度生成模型视为概率变换函数。尽管各类生成模型（自编码器、自回归模型、生成对抗网络、归一化流、扩散模型、流匹配）在结构和训练方法上存在明显差异，但它们均通过将预定义的简单分布变换为复杂的目标数据分布来实现生成。这一统一视角促进了不同模型架构间的方法改进转移，并为发展通用理论框架奠定基础，有望推动更高效、更有效的生成建模技术的发展。
原文摘要 · Abstract (English)
This paper introduces a unified theoretical perspective that views deep generative models as probability transformation functions. Despite the apparent differences in architecture and training methodologies among various types of generative models - autoencoders, autoregressive models, generative adversarial networks, normalizing flows, diffusion models, and flow matching - we demonstrate that they all fundamentally operate by transforming simple predefined distributions into complex target data distributions. This unifying perspective facilitates the transfer of methodological improvements between model architectures and provides a foundation for developing universal theoretical approaches, potentially leading to more efficient and effective generative modeling techniques.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。