Pinned Loading

1. opensmi opensmi Public

   Python

2. VisAttnSink VisAttnSink Public

   [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models

   Python 92 11

3. LocalizationHeads LocalizationHeads Public

   [CVPR 2025 Highlight] Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding

   Python 61 6

4. tora tora Public

   [NeurIPS 2025] Rare Text Semantics Were Always There in Your Diffusion Transformer

   12 1

5. fullstack-deeplearning fullstack-deeplearning Public

   Python 6 1