MMFlash: Faster Speculative Decoding for Vision-Language Models
MMFlash improves speculative decoding for vision-language models by focusing drafter training on visually dependent tokens and using sparse attention for long videos.
ls ./papers | grep "#Long-video understanding"
Trending AI research papers from Hugging Face, summarized in plain language: what each paper does, why it matters and where to read more.
1 paper · #Long-video understanding
MMFlash improves speculative decoding for vision-language models by focusing drafter training on visually dependent tokens and using sparse attention for long videos.