Kavli Affiliate: Wei Gao | First 5 Authors: Xuan Zhang, Cunxiao Du, Sicheng Yu, Jiawei Wu, Fengzhuo Zhang | Summary: Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually very […]
Continue.. Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs