A PyTorch implementation of VL-JEPA from the paper "VL-JEPA: Joint Embedding Predictive Architecture for Vision-language" (arXiv:2512.10942v2). vl-jepa/ ├── src/ │ ├── model.py # Core VL-JEPA model ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results