Casa Vl Fusion

Replace token-insertion for fusing vision and language with efficient cross-attention that maintains separate text self-attention. Enables text tokens to attend images within local windows, preserves gist tokens from prior images, and maintains near-constant memory costs for streaming video—more practical than direct token insertion for resource-constrained applications.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 038f3d2f58

Frequently asked questions

npx get-skill add adu2021/casa-vl-fusion