对 Platonic Representation Hypothesis 的再审视：对齐在何处出现

作者首先定位了单模态模型之间的对齐出现在哪些模型层和表征维度上，并指出表征相似度指标容易被模型深度和宽度混淆，需要设置合适基线才能解读。研究发现，只要字幕足够干净且信息充分，PRH 的能力-对齐趋势在更新的语言模型上依然成立。

论文还在多个数据集上引入了单模态与多模态基线来 contextualize 跨模态对齐。结果显示，单模态模型的跨模态表征对齐可以超过显式对齐的视觉-语言模型，但仍显著低于同模态模型之间的对齐。

代码已在 GitHub（ExplainableML/prh-closer-look）开源。

Where Does Alignment Emerge and What Does It Mean? A Closer Look at the Platonic Representation Hypothesis

The Platonic Representation Hypothesis (PRH) suggests that neural networks are converging toward similar representation spaces. As language models become more capable, their representations are aligning with those of vision models. However, recent work has questioned whether this trend continues to hold for newer language models. Moreover, it has been shown that representation similarity metrics can be confounded by model depth and width, requiring appropriate baselines for interpretation. In this work, we first investigate where alignment emerges between unimodal models across model layers and representation dimensions. Next, we find that the PRH capability-alignment trend persists for newer models as long as the captions are sufficiently clean and informative. Finally, we contextualize cross-modal alignment, introducing unimodal and multimodal baselines on various datasets. Our results show that the cross-modal representational alignment of unimodal models can surpass that of explicitly aligned vision-language models, but remains substantially behind the alignment observed for models of the same modality. Code is available at https://github.com/ExplainableML/prh-closer-look.

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：PRH、表征学习、多模态、可解释性，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Julia Herbst, Simon Roschmann, Quentin Bouniot, Zeynep Akata），经 AITOP 多维评分管线结构化提炼。