Pinned Loading

1. scaling_on_scales scaling_on_scales Public

   When do we not need larger vision models?

   Python 369 12

2. NVlabs/VILA NVlabs/VILA Public

   VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

   Python 2.9k 238

3. TOAST TOAST Public

   Official code for "TOAST: Transfer Learning via Attention Steering"

   Python 188 11

4. AbSViT AbSViT Public

   Official code for "Top-Down Visual Attention from Analysis by Synthesis" (CVPR 2023 highlight)

   Jupyter Notebook 165 12