1
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs
ACL 2025论文提出Sparse-to-Dense方法，实现视频理解在LLM中的无损加速，堪称"免费午餐
arXiv:2505.19155v2 Announce Type: replace-cross Abstract: Due to the auto-regressive nature of current video large language models (Video-LLMs), the i…