The last decade has seen tremendous progress in our ability to generate realistic-looking data, be it images, text, audio, or video. Here, we discuss the closely related problem of quantifying realism, that is, designing functions that can reliably tell realistic data from unrealistic data. This problem turns out to be significantly harder to solve and remains poorly understood, despite its prevalence in machine learning and recent breakthroughs in generative AI. Drawing on insights from algorithmic information theory, we discuss why this problem is challenging, why a good generative model alone is insufficient to solve it, and what a good solution would look like. In particular, we introduce the notion of a universal critic, which unlike adversarial critics does not require adversarial training. While universal critics are not immediately practical, they can serve both as a North Star for guiding practical implementations and as a tool for analyzing existing attempts to capture realism.

翻译：过去十年中，我们在生成逼真数据（无论是图像、文本、音频还是视频）方面取得了巨大进步。本文讨论与之密切相关的量化真实感问题，即设计能够可靠区分真实数据与不真实数据的函数。尽管这一问题在机器学习领域普遍存在，且生成式AI近期取得突破性进展，但事实证明解决该问题要困难得多，且至今仍未被充分理解。借助算法信息论的洞见，我们探讨为何该问题具有挑战性，为何仅凭优秀的生成模型不足以解决它，以及一个理想的解决方案应具备何种特征。具体而言，我们引入了“通用批评者”这一概念，与对抗式批评者不同，它无需对抗训练。虽然通用批评者在当下并不实用，但它既可作为指导实际实现的北极星，也可作为分析现有真实感建模尝试的工具。