English
Related papers

Related papers: Language-Guided Temporal Token Pruning for Efficie…

200 papers

Video Large Language Models (Video LLMs) have achieved impressive performance on video-and-language tasks, such as video question answering. However, most existing Video LLMs neglect temporal information in video data, leading to struggles…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Zi-Yuan Hu , Yiwu Zhong , Shijia Huang , Michael R. Lyu , Liwei Wang

While Video Large Language Models (Video-LLMs) have demonstrated remarkable performance across general video understanding benchmarks-particularly in video captioning and descriptive tasks-they consistently underperform on tasks that…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Sameep Vani , Shreyas Jena , Maitreya Patel , Chitta Baral , Somak Aditya , Yezhou Yang

Vision-Language Models (VLMs) demand substantial computational resources during inference, largely due to the extensive visual input tokens for representing visual information. Previous studies have noted that visual tokens tend to receive…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Cheng Yang , Yang Sui , Jinqi Xiao , Lingyi Huang , Yu Gong , Chendi Li , Jinghua Yan , Yu Bai , Ponnuswamy Sadayappan , Xia Hu , Bo Yuan

Video Large Language Models (VLLMs) excel in video understanding, but their excessive visual tokens pose a significant computational challenge for real-world applications. Current methods aim to enhance inference efficiency by visual token…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Junpeng Ma , Qizhe Zhang , Ming Lu , Zhibin Wang , Qiang Zhou , Jun Song , Shanghang Zhang

In AI research, the optimization of Large Language Models (LLMs) remains a significant challenge, crucial for advancing the field's practical applications and sustainability. Building upon the foundational work of Professor Song Han's lab…

Computation and Language · Computer Science 2023-12-21 Tim Valicenti , Justice Vidal , Ritik Patnaik

Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost grows rapidly with the number of visual tokens, especially for high-resolution images and long videos. Existing attention-based methods…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Hongyu Lu , Feng Zhang , Wenwei Jin , Huanling Hu , Tianjun Shi , Shikai Jiang , Yao Hu , Jiawei Li

The remarkable natural language understanding, reasoning, and generation capabilities of large language models (LLMs) have made them attractive for application to video understanding, utilizing video tokens as contextual input. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Jiaqi Xu , Cuiling Lan , Wenxuan Xie , Xuejin Chen , Yan Lu

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…

Computer Vision and Pattern Recognition · Computer Science 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…

Computer Vision and Pattern Recognition · Computer Science 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

As the computational needs of Large Vision-Language Models (LVLMs) increase, visual token pruning has proven effective in improving inference speed and memory efficiency. Traditional pruning methods in LVLMs predominantly focus on attention…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Bozhi Luan , Wengang Zhou , Hao Feng , Zhe Wang , Xiaosong Li , Houqiang Li

Large Vision-Language Models (LVLMs) process multimodal inputs consisting of text tokens and vision tokens extracted from images or videos. Due to the rich visual information, a single image can generate thousands of vision tokens, leading…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Zicong Tang , Ziyang Ma , Suqing Wang , Zuchao Li , Lefei Zhang , Hai Zhao , Yun Li , Qianren Wang

Efficient vision-language understanding of large Remote Sensing Images (RSIs) is meaningful but challenging. Current Large Vision-Language Models (LVLMs) typically employ limited pre-defined grids to process images, leading to information…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Junwei Luo , Yingying Zhang , Xue Yang , Kang Wu , Qi Zhu , Lei Liang , Jingdong Chen , Yansheng Li

Video-language models (VLMs) face rapid inference costs as visual token counts scale with video length. For example, 32 frames at $448{\times}448$ resolution already yield >8,000 visual tokens in Qwen3-VL, making LLM prefill the dominant…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Simin Huo , Ning LI

Video Temporal Grounding (VTG) aims to precisely identify video event segments in response to textual queries. The outputs of VTG tasks manifest as sequences of events, each defined by precise timestamps, saliency scores, and textual…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Zuhao Yang , Yingchen Yu , Yunqing Zhao , Shijian Lu , Song Bai

Video Large Language Models (VideoLLMs) have demonstrated impressive capabilities in video understanding, yet the massive number of input video tokens incurs a significant computational burden for deployment. Existing methods mainly prune…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Yansong Guo , Chaoyang Zhu , Jiayi Ji , Jianghang Lin , Liujuan Cao

In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video. Benefiting from fine-grained 3D visual…

Computer Vision and Pattern Recognition · Computer Science 2023-10-05 Yimeng Zhang , Xin Chen , Jinghan Jia , Sijia Liu , Ke Ding

Vision-Language Models (VLMs), such as CLIP, have achieved significant zero-shot performance on downstream tasks with various fine-tuning adaptation methods. However, recent studies have proven that adversarial attacks can significantly…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Jia-Wei Hai , Yijun Wang , Xiu-Shen Wei

Deploying transformer models in practice is challenging due to their inference cost, which scales quadratically with input sequence length. To address this, we present a novel Learned Token Pruning (LTP) method which adaptively removes…

Computation and Language · Computer Science 2022-06-06 Sehoon Kim , Sheng Shen , David Thorsley , Amir Gholami , Woosuk Kwon , Joseph Hassoun , Kurt Keutzer

Recent advances in long video understanding typically mitigate visual redundancy through visual token pruning based on attention distribution. However, while existing methods employ post-hoc low-response token pruning in decoder layers,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Yongdong Luo , Wang Chen , Xiawu Zheng , Weizhong Huang , Shukang Yin , Haojia Lin , Chaoyou Fu , Jinfa Huang , Jiayi Ji , Jiebo Luo , Rongrong Ji

Token reduction is an effective way to accelerate long-video vision-language models (VLMs), but most existing methods are designed for dense Transformers and do not directly account for hybrid architectures that interleave attention with…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Jindong Jiang , Amala Sanjay Deshmukh , Kateryna Chumachenko , Karan Sapra , Zhiding Yu , Guilin Liu , Andrew Tao , Pavlo Molchanov , Jan Kautz , Wonmin Byeon