V-JEPA 2 Collection A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13, 2025 • 200
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning Paper • 2603.14482 • Published 14 days ago • 23
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 Text Generation • 67B • Updated 5 days ago • 1.2M • 233