Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More

17 February 2025

Papers citing "Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More"

7 / 7 papers shown

Title
VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models Ce Zhang Kaixin Ma Tianqing Fang Wenhao Yu Hongming Zhang Zhisong Zhang Yaqi Xie Katia Sycara Haitao Mi Dong Yu VLM 24 0 0 28 May 2025
ToDRE: Visual Token Pruning via Diversity and Task Awareness for Efficient Large Vision-Language Models Duo Li Zuhao Yang Shijian Lu VLM 35 0 0 24 May 2025
QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design Benjamin Schneider Dongfu Jiang Chao Du Tianyu Pang Wenhu Chen VLM 20 0 0 22 May 2025
FLASH: Latent-Aware Semi-Autoregressive Speculative Decoding for Multimodal Tasks Zihua Wang Ruibo Li Haozhe Du Joey Tianyi Zhou Yu Zhang Xu Yang MLLM 61 0 0 19 May 2025
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Linli Yao You Li Y. X. Wei Lei Li Shuhuai Ren ... Sida Li Dianbo Sui Qi Liu Yanzhe Zhang Xu Sun 71 1 0 24 Apr 2025
LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts Yimu Wang Mozhgan Nasr Azadani Sean Sedwards Krzysztof Czarnecki MLLM MoE 72 0 0 07 Apr 2025
VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers Ruanjun Li Yuedong Tan Yuanming Shi Jiawei Shao VLM 295 0 0 12 Mar 2025