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, b
Joint-embedding predictive architectures trained on aligned multi-modal observations converge to shared representations with far greater efficiency than next-token prediction, demonstrating that positive view design—not scale alone—drives cross-modal alignment.
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. We turn the hypothesis into a theorem. First, we prove a Platonic Representation Theorem: Joint-Embedding Predictive Architectures (JEPAs) trained separately on any number of modalities learn the same representation up to one rotation whenever their positive pairs are two observations of one scene--good views--and their misalignment is bounded otherwise. Second, we show that next-token prediction is a JEPA with bad views, parts of…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Proving and Improving the Platonic Representation Hypothesis with JEPAs was first seen on Hugging Face · Daily papers on Oct 30, 2026. Since then it has appeared in 9 checks on 2 different days. Its best position was #5 of 30, reached on Oct 30, 21:28 UTC. It is #6 right now, holding steady at #6 over the last 6 checks.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
▲ as reported by Hugging Face.
Yes. As of Oct 31, 09:28 UTC it is #6, holding steady at #6 over the last 6 checks.
#5 on Hugging Face · Daily papers, on Oct 30, 21:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Oct 30, 2026 and has been on the list on 2 days (9 checks) since.