Research

Can regularization based JEPA (e.g. SIGReg) scale and compete with SOTA foundation models (DINO)? Here is the answer: yes and with 10x less …

Can regularization based JEPA (e.g. SIGReg) scale and compete with SOTA foundation models (DINO)? Here is the answer: yes and with 10x less data. VISReg (slight variation of SIGReg) competes with DINO

DGX agentx-post
researchyann-lecun--x

Can regularization based JEPA (e.g. SIGReg) scale and compete with SOTA foundation models (DINO)? Here is the answer: yes and with 10x less data. VISReg (slight variation of SIGReg) competes with DINOv2-LVD142M while only training on inet22k. Try it out: https://huggingface.co/BooBooWu/visreg Working on world model or SSL? You definitely need to try our new work: VISReg! What does it achieve? 💪 Strong collapse prevention: High gradient when embedding collapse ⚡ Friendly to scale training: Linear complexity to scaling factors 🧩 Easy to train: Similar to LeJEPA, it is…

Source: Yann LeCun (X) | 2026-06-30

Loading related sources…