让扩散模型自我进化，生成更真实图像。
Generating on Generated: An Approach Towards Self-Evolving Diffusion Models
- 用提示工程和筛选确保生成图像与真实感知对齐。
- 通过偏好采样过滤幻觉内容，提升生成质量。
- 基于分布加权惩罚幻觉样本，适合研究自进化AI。
递归自我改进（RSI）使智能系统能自主优化自身能力。本文探索将RSI应用于文本到图像的扩散模型，解决由合成数据引发的训练崩溃问题。我们识别出两个关键成因：缺乏感知一致性与生成幻觉的累积。为此提出三种策略：(1) 提示构建与过滤流程，促进生成具有感知一致性的数据；(2) 偏好采样方法，识别人类偏好的样本并剔除生成幻觉；(3) 基于分布的加权方案，对包含幻觉错误的样本进行惩罚。大量实验验证了这些方法的有效性。
原文摘要 · Abstract (English)
Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities. This paper explores the application of RSI in text-to-image diffusion models, addressing the challenge of training collapse caused by synthetic data. We identify two key factors contributing to this collapse: the lack of perceptual alignment and the accumulation of generative hallucinations. To mitigate these issues, we propose three strategies: (1) a prompt construction and filtering pipeline designed to facilitate the generation of perceptual aligned data, (2) a preference sampling method to identify human-preferred samples and filter out generative hallucinations, and (3) a distribution-based weighting scheme to penalize selected samples with hallucinatory errors. Our extensive experiments validate the effectiveness of these approaches.
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。