English
Related papers

Related papers: DyMU: Dynamic Merging and Virtual Unmerging for Ef…

200 papers

Video large language models (VLLMs) have significantly advanced recently in processing complex video content, yet their inference efficiency remains constrained because of the high computational cost stemming from the thousands of visual…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Keda Tao , Can Qin , Haoxuan You , Yang Sui , Huan Wang

Large Multimodal Models (LMMs) are powerful tools that are capable of reasoning and understanding multimodal information beyond text and language. Despite their entrenched impact, the development of LMMs is hindered by the higher…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Vittorio Pippi , Matthieu Guillaumin , Silvia Cascianelli , Rita Cucchiara , Maximilian Jaritz , Loris Bazzani

The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Han Wang , Yuxiang Nie , Yongjie Ye , Deng GuanYu , Yanjie Wang , Shuai Li , Haiyang Yu , Jinghui Lu , Can Huang

Large Multimodal Models (LMMs) have shown significant visual reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically take in a fixed and large amount of visual tokens, such as the penultimate layer…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Yuzhang Shang , Mu Cai , Bingxin Xu , Yong Jae Lee , Yan Yan

Recent advancements in multimodal large language models (MLLMs) have opened new avenues for video understanding. However, achieving high fidelity in zero-shot video tasks remains challenging. Traditional video processing methods rely…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Yiming Zhang , Zhuokai Zhao , Zhaorun Chen , Zenghui Ding , Xianjun Yang , Yining Sun

Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Hanxun Yu , Wentong Li , Xuan Qu , Song Wang , Junbo Chen , Jianke Zhu

Typical video modeling methods, such as LLava, represent videos as sequences of visual tokens, which are then processed by the LLM backbone for effective video understanding. However, this approach leads to a massive number of visual…

Computation and Language · Computer Science 2025-06-05 Hongzhi Zhang , Jingyuan Zhang , Xingguang Ji , Qi Wang , Fuzheng Zhang

Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. Existing efficiency approaches either merge redundant visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Aditya Kumar Singh , Hitesh Kandala , Pratik Prabhanjan Brahma , Zicheng Liu , Emad Barsoum

The quadratic cost of self-attention in Vision Transformers (ViTs) constitutes a fundamental bottleneck for practical deployment, motivating a vibrant line of research on token reduction. Among existing approaches, token merging (ToMe) has…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Semi Lee , Hyejin Go , Hyesong Choi

Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-free acceleration in ViTs, we improve token merging by…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Jung Hwan Heo , Seyedarmin Azizi , Arash Fayyazi , Massoud Pedram

Multi-modal large language models (MLLMs) utilizing instruction-following data, such as LLaVA, have achieved great progress in the industry. A major limitation in these models is that visual tokens consume a substantial portion of the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Ke Wang , Hong Xuan

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Yiwu Zhong , Zhuoming Liu , Yin Li , Liwei Wang

Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks. However, the increasing demand for high-resolution image and long-video understanding results in substantial token counts,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Junjie Chen , Xuyang Liu , Zichen Wen , Yiyu Wang , Siteng Huang , Honggang Chen

Current multimodal large language models (MLLMs) face significant challenges in visual document understanding (VDU) tasks due to the high resolution, dense text, and complex layouts typical of document images. These characteristics demand a…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Jiaxin Zhang , Wentao Yang , Songxuan Lai , Zecheng Xie , Lianwen Jin

Recent token reduction methods for Vision Transformers (ViTs) incorporate token merging, which measures the similarities between token embeddings and combines the most similar pairs. However, their merging policies are directly dependent on…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Dong Hoon Lee , Seunghoon Hong

Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Yulin Li , Haokun Gui , Ziyang Fan , Junjie Wang , Bin Kang , Bin Chen , Zhuotao Tian

The excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation. To gain insights into this problem, we first conduct extensive…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Qiong Wu , Wenhao Lin , Yiyi Zhou , Weihao Ye , Zhanpeng Zen , Xiaoshuai Sun , Rongrong Ji

Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Junshan Hu , Jialiang Mao , Zhikang Liu , Zhongpu Xia , Peng Jia , Xianpeng Lang

Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Hyun Lee , Hyemin Jeong , Yejin Kim , Hyungwook Choi , Hyunsoo Cho , Soo Kyung Kim , Joonseok Lee

Multimodal large language models (MLLMs) demand considerable computations for inference due to the extensive parameters and the additional input tokens needed for visual information representation. Herein, we introduce Visual Tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Zhihang Lin , Mingbao Lin , Luxi Lin , Rongrong Ji
‹ Prev 1 2 3 10 Next ›