Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
The Platonic Representation Hypothesis posits that neural networks trained on different modalities (e.g., text and images) converge toward a shared representation of reality. If true, this has significant implications for whether modality choice matters at all. In this paper, we show that the evidence for this claim is substantially weaker than subsequent work suggests. The mutual $k$-nearest-neighbor metric used on 1024 text-image pairs in the original study captures only coarse structure. To keep the alignment from collapsing as one scales up the data, $k$ has to grow proportionally, undercutting the argument for fine-grained representational convergence. The reported increase in alignm...
| Authors | A. Sophia Koepke, Daniil Zverev, Shiry Ginosar et al. |
|---|---|
| Primary category | cs.CV |
| Published | 20 April 2026 |
| Last updated at source | 1 October 2026 |
Connected in the knowledge graph
- askoepke/wit_1m_recaptionedDataset · cited by
Models and datasets referencing this paper
- askoepke/wit_1m_recaptionedDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.