模型崩溃：关于递归、噪声和未知的机器视觉
Model Collapse: On Recursion, Noise, and Uncharted Machine Visions
- Bibliotheca Hertziana – Max Planck Institute for Art History（赫兹利亚图书馆——马克斯·普朗克艺术史研究所）
- Sorbonne Nouvelle（新索邦大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究模型崩溃现象，通过历史视频合成技术和当代机器学习艺术应用案例，探讨递归训练揭示的AI生成数据依赖性本质，指出崩溃挑战超人类主义理想，引入美学视角，视噪声和递归为理解艺术创作与AI生态系统的关键概念。
AI中文摘要：
自2023年以来，计算机科学家已发出对模型崩溃的警告，即人工智能生成的输出污染训练集，逐步降低模型性能。这是一种正反馈驱动的失败，会产生单词重复或像素噪声等影响，最终导致意义和连贯性丧失。从创造性角度看，崩溃不仅是故障，还像递归镜子，引发系统自我审视时会发生什么的问题。本文通过历史视频合成技术和当代机器学习艺术应用的案例研究，探讨递归训练揭示的人工智能生成数据的依赖性本质。认为崩溃的潜在影响挑战了超人类主义理想，同时引入美学视角，将噪声和递归定位为理解艺术创作和人工智能生态系统的关键概念。
英文摘要：
Since 2023, computer scientists have warned against model collapse -- the contamination of training sets with AI-generated outputs that progressively degrade model performance. Exemplifying a positive-feedback-driven failure, it produces effects such as word repetition or pixel noise, ultimately leading to a loss of meaning and coherence -- at least from an engineering standpoint. From a creative one, however, collapse is not merely a breakdown: it also functions as a recursive mirror that recalls early analog video feedback experiments, raising once again the question of what happens when a system turns inward and sees itself. In such cases, so-called machine vision no longer transmits the world (as in tele-vision) but increasingly generates worlds from within. Drawing on media archaeology through case studies of both historical video synthesis techniques and contemporary artistic uses of machine learning, this paper examines what recursive training reveals about the dependent nature of AI-generated data. It argues that the potential effects of collapse challenge transhumanist ideals while inviting an aesthetic perspective, positioning noise and recursion as key concepts for understanding both artmaking and the AI ecosystem. Distributing agency across scales and networks, the latter currently remains reliant on new human-produced content, particularly within foundation models trained on massive datasets.
