Research
🔥 We introduce LeVLJEPA: the first fully non-contrastive end-to-end vision-language pretraining method competitive with CLIP & SigLIP 💪🏼 …
🔥 We introduce LeVLJEPA: the first fully non-contrastive end-to-end vision-language pretraining method competitive with CLIP & SigLIP 💪🏼 👀 No negatives. No temperature. No momentum encoder. No teacher
🔥 We introduce LeVLJEPA: the first fully non-contrastive end-to-end vision-language pretraining method competitive with CLIP & SigLIP 💪🏼 👀 No negatives. No temperature. No momentum encoder. No teacher-student. TL;DR: LeVLJEPA learns image to text structure by prediction: each modality predicts the other's embedding, while SIGReg keeps each embedding isotropic Gaussian. 🧵 📄 https://arxiv.org/abs/2607.00784 Media
Source: Yann LeCun (X) | 2026-07-02