casa-vl-fusion

【效率与协作】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-cons…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准