用自先验机制让模型自发完成镜中识我，无需奖励信号。
Active Inference with a Self-Prior in the Mirror-Mark Task
- 基于自先验的主动推断框架，通过多模态感知学习身体常态。
- 70%概率自主移除镜中面部贴纸，且行为后预期自由能显著下降。
- 适用于研究自我意识发展，尤其适合认知建模与神经科学交叉者。
镜像自我识别测试用于评估个体是否能通过镜中影像识别自身标记，是自知力的重要指标。本研究提出一种计算模型，仅通过单一机制——自先验（self-prior），无需外部奖励即可自发产生该行为。自先验采用Transformer实现，学习熟悉多模态经验的密度分布；当出现新标记时，与该分布的偏差通过主动推断驱动目标导向行为。模拟婴儿仅依赖视觉与本体感觉，未使用触觉输入，在约70%情况下成功发现并移除镜中面部贴纸，且贴纸移除后预期自由能显著下降，证实自先验可作为区分自我与非我的内部标准。跨模态采样进一步表明，自先验捕捉了视觉-本体感觉关联，构成概率性身体表征。结果为镜像测试中的核心行为提供了简洁的计算解释，并支持自由能原理作为探究自我意识发展起源的统一假说。代码已开源：https://github.com/kim135797531/self-prior-mirror
原文摘要 · Abstract (English)
The mirror self-recognition test evaluates whether a subject touches a mark on its own body that is visible only in a mirror, and is widely used as an indicator of self-awareness. In this study, we present a computational model in which this behavior emerges spontaneously through a single mechanism, the self-prior, without any external reward. The self-prior, implemented with a Transformer, learns the density of familiar multisensory experiences; when a novel mark appears, the discrepancy from this learned distribution drives mark-directed behavior through active inference. A simulated infant, relying solely on vision and proprioception without tactile input, discovered a sticker placed on its own face in the mirror and removed it in approximately 70% of cases without any explicit instruction. Expected free energy decreased significantly after sticker removal, confirming that the self-prior operates as an internal criterion for distinguishing self from non-self. Cross-modal sampling further demonstrated that the self-prior captures visual--proprioceptive associations, functioning as a probabilistic body schema. These results provide a concise computational account of the key behavior observed in the mirror test and suggest that the free energy principle can serve as a unifying hypothesis for investigating the developmental origins of self-awareness. Code is available at: https://github.com/kim135797531/self-prior-mirror
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。