中文
相关论文

相关论文: Skip-Vision: Efficient and Scalable Acceleration o…

200 篇论文

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,…

计算机视觉与模式识别 · 计算机科学 2026-02-26 Junjie Chen , Xuyang Liu , Zichen Wen , Yiyu Wang , Siteng Huang , Honggang Chen

Transformer-based Vision-Language Models (VLMs) have achieved impressive performance on tasks such as image captioning, object recognition, and visual reasoning, but their high computational cost hinders deployment in latency-sensitive…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Lianming Huang , Haibo Hu , Qiao Li , Xin He , Nan Guan , Chun Jason Xue

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…

计算机视觉与模式识别 · 计算机科学 2024-08-30 Shiwei Wu , Joya Chen , Kevin Qinghong Lin , Qimeng Wang , Yan Gao , Qianli Xu , Tong Xu , Yao Hu , Enhong Chen , Mike Zheng Shou

Prevailing Multimodal Large Language Models (MLLMs) encode the input image(s) as vision tokens and feed them into the language backbone, similar to how Large Language Models (LLMs) process the text tokens. However, the number of vision…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Shiyu Zhao , Zhenting Wang , Felix Juefei-Xu , Xide Xia , Miao Liu , Xiaofang Wang , Mingfu Liang , Ning Zhang , Dimitris N. Metaxas , Licheng Yu

Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Zichuan Lin , Yicheng Liu , Yang Yang , Lvfang Tao , Deheng Ye

Recent Large Vision-Language Models (LVLMs) have advanced multi-modal understanding by incorporating finer-grained visual perception and encoding. However, such methods incur significant computational costs due to longer visual token…

计算机视觉与模式识别 · 计算机科学 2026-02-02 Ce Zhang , Kaixin Ma , Tianqing Fang , Wenhao Yu , Hongming Zhang , Zhisong Zhang , Haitao Mi , Dong Yu

Large Vision-Language Models (LVLMs) incur high computational costs due to significant redundancy in their visual tokens. To effectively reduce this cost, researchers have proposed various visual token pruning methods. However, existing…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Wen Luo , Peng Chen , Xiaotao Huang , LiQun Huang

Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual…

计算机视觉与模式识别 · 计算机科学 2025-12-24 Kaitong Cai , Jusheng Zhang , Jing Yang , Yijia Fan , Pengtao Xie , Jian Wang , Keze Wang

Visual token pruning is a promising approach for reducing the computational cost of vision-language models (VLMs), and existing methods often rely on early pruning decisions to improve efficiency. While effective on coarse-grained reasoning…

计算机视觉与模式识别 · 计算机科学 2026-02-04 Chen Qian , Xinran Yu , Danyang Li , Guoxuan Chi , Zheng Yang , Qiang Ma , Xin Miao

In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens. To address this, most existing methods learn a network to…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Yuan Zhang , Chun-Kai Fan , Junpeng Ma , Wenzhao Zheng , Tao Huang , Kuan Cheng , Denis Gudovskiy , Tomoyuki Okuno , Yohei Nakata , Kurt Keutzer , Shanghang Zhang

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

计算与语言 · 计算机科学 2024-02-27 Zekun Wang , Jingchang Chen , Wangchunshu Zhou , Haichao Zhu , Jiafeng Liang , Liping Shan , Ming Liu , Dongliang Xu , Qing Yang , Bing Qin

Prompt tuning (PT) has long been recognized as an effective and efficient paradigm for transferring large pre-trained vision-language models (VLMs) to downstream tasks by learning a tiny set of context vectors. Nevertheless, in this work,…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Shihan Wu , Ji Zhang , Pengpeng Zeng , Lianli Gao , Jingkuan Song , Heng Tao Shen

Although Large Vision Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, their scalability and deployment are constrained by massive computational requirements. In particular, the massive amount of…

机器学习 · 计算机科学 2026-04-14 Surendra Pathak , Bo Han

Vision transformers are known to be more computationally and data-intensive than CNN models. These transformer models such as ViT, require all the input image tokens to learn the relationship among them. However, many of these tokens are…

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…

计算机视觉与模式识别 · 计算机科学 2025-04-07 Junshan Hu , Jialiang Mao , Zhikang Liu , Zhongpu Xia , Peng Jia , Xianpeng Lang

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…

计算机视觉与模式识别 · 计算机科学 2025-12-25 Putu Indah Githa Cahyani , Komang David Dananjaya Suartana , Novanto Yudistira

This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs). Our approach employs a sequence of visual resamplers that capture visual details at various…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Ziyuan Huang , Kaixiang Ji , Biao Gong , Zhiwu Qing , Qinglong Zhang , Kecheng Zheng , Jian Wang , Jingdong Chen , Ming Yang

Large multimodal models (LMMs) suffer significant computational challenges due to the high cost of Large Language Models (LLMs) and the quadratic complexity of processing long vision token sequences. In this paper, we explore the spatial…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Hao Tang , Chengchao Shen

Vision-language Models (VLMs) have made significant strides in visual understanding and query response generation, but often face challenges of high computational cost and inference latency due to autoregressive decoding. In this work, we…

机器学习 · 计算机科学 2025-10-28 Divya Jyoti Bajpai , Manjesh Kumar Hanawal

Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quality video data. This paper addresses the challenge by…

计算机视觉与模式识别 · 计算机科学 2024-06-13 Shimin Chen , Yitian Yuan , Shaoxiang Chen , Zequn Jie , Lin Ma
‹ 上一页 1 2 3 10 下一页 ›