X · @ylecun
· X / Twitter
RT Randall Balestriero: Oops, SIGReg did it again! Large scale (CC12M->Datacomp-L) vision-language JEPA pretraining beats CLIP and SigLIP objectives! …
RT Randall BalestrieroOops, SIGReg did it again! Large scale (CC12M->Datacomp-L) vision-language JEPA pretraining beats CLIP and SigLIP objectives! Thanks to SIGReg, our LeVLJEPA has no collapse, no EMA, no stop-gradient, no negatives, no problem! Checkpoints/demo are live: http://levljepa.github.ioLukas Kuhn: 🔥 We int