visor-sparse-vision-language-interaction

【设计与创意】Optimize vision-language model inference by sparsifying the interactions between vision and language tokens instead of compressing images. Uses a dynamic policy to allocate visual computation per sample based on complexity, enabling a universal network across different compute budgets. Maintains high-resolution reasoning when needed. Use when deployi…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准