Proving and Improving the Platonic Representation Hypothesis with JEPAs
- View PDF HTML (experimental) Abstract:Whether models trained on different modalities converge to the same representation of the world is central to AI.
- The Platonic Representation Hypothesis (PRH) conjectures that they do as they scale, but without a proof it offers neither a guarantee nor a recipe.
Unverified
- View PDF HTML (experimental) Abstract:Whether models trained on different modalities converge to the same representation of the world is central to AI.
- The Platonic Representation Hypothesis (PRH) conjectures that they do as they scale, but without a proof it offers neither a guarantee nor a recipe.
Sources: Arxiv