Where Does Alignment Emerge and What Does It Mean? A Closer Look at the Platonic Representation Hypothesis
Organizations: Helmholtz Munich · Technical University of Munich · Munich Center for Machine Learning · LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France
Abstract
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.
Figures & tables
Appendix figures & tables12 assets
Supplementary material from the paper’s appendix.
Appendix
| WIT | COCO | DOCCI 100% | ||||
|---|---|---|---|---|---|---|
| VLM | Final | Max | Final | Max | Final | Max |
| CLIP | 0.199 | 0.199 | ||||
| SigLIP 2 | 0.079 | 0.079 | ||||
| Q3-VL | 0.218 | 0.224 | ||||
Platonic Representation Hypothesis
Platonic Representation Hypothesis asks whether independently trained models converge on shared internal structures that reflect the world.
See all 23 papers