Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs

25 May 2025

Papers citing "Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs"

5 / 5 papers shown

Title
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms Yunlong Hou Fengzhuo Zhang Cunxiao Du Xuan Zhang Jiachun Pan Tianyu Pang Chao Du Vincent Y. F. Tan Zhuoran Yang OffRL 192 2 0 21 May 2025
Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference Zhihang Lin Mingbao Lin Luxi Lin Rongrong Ji 141 52 0 28 Jan 2025
Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding Yao Teng Han Shi Xian Liu Xuefei Ning Guohao Dai Yu Wang Zhenguo Li Xihui Liu 185 23 0 02 Oct 2024
MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding Jian Chen Vashisth Tiwari Ranajoy Sadhukhan Zhuoming Chen Jinyuan Shi Ian En-Hsu Yen Ian En-Hsu Yen Avner May Tianqi Chen Beidi Chen LRM 273 45 0 20 Aug 2024
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty Yuhui Li Fangyun Wei Chao Zhang Hongyang R. Zhang 304 213 0 26 Jan 2024