sttm-spatio-temporal-token-merging-video

【效率与协作】Accelerate video LLMs by 2× with minimal accuracy loss using training-free spatio-temporal token merging that exploits video redundancy through quadtree-based spatial compression and temporal frame similarity, enabling efficient multi-turn reasoning with KV cache reuse.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准