Baifeng Shi bfshi

• University of California, Berkeley

• Berkeley, CA
• bfshi.github.io

Pinned Loading

1. Scaling Vision Pre-Training to 4K Resolution

   Python 221 10

2. When do we not need larger vision models?

   Python 413 15

3. 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 3.8k 315

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

   Python 188 10

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

   Jupyter Notebook 167 13