English
Related papers

Related papers: Static or Dynamic: Towards Query-Adaptive Token Se…

200 papers

Processing long-form videos with Video Large Language Models (Video-LLMs) is computationally prohibitive. Current efficiency methods often compromise fine-grained perception through irreversible information disposal or inhibit long-range…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Handong Li , Zikang Liu , Longteng Guo , Tongtian Yue , Yepeng Tang , Xinxin Zhu , Chuanyang Zheng , Ziming Wang , Zhibin Wang , Jun Song , Cheng Yu , Bo Zheng , Jing Liu

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

Machine Learning · Computer Science 2025-02-19 Kan Zhu , Tian Tang , Qinyu Xu , Yile Gu , Zhichen Zeng , Rohan Kadekodi , Liangyu Zhao , Ang Li , Arvind Krishnamurthy , Baris Kasikci

Despite the recent advances in the video understanding ability of multimodal large language models (MLLMs), long video understanding remains a challenge. One of the main issues is that the number of vision tokens grows linearly with video…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Siyou Li , Huanan Wu , Juexi Shao , Yinghao Ma , Yujian Gan , Yihao Luo , Yuwei Wang , Dong Nie , Lu Wang , Wenqing Wu , Le Zhang , Massimo Poesio , Juntao Yu

The application of Large Multimodal Models (LMMs) to long-form video understanding is constrained by limited context lengths and the computationally prohibitive cost of processing dense video tokens. Consequently, recent research has…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Jialuo Li , Bin Li , Jiahao Li , Yan Lu

Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted metrics or static/snapshot-based criteria to estimate…

Machine Learning · Computer Science 2026-05-14 Suorong Yang , Fangjian Su , Hai Gan , Ziqi Ye , Jie Li , Baile Xu , Furao Shen , Soujanya Poria

Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual tokens required. To improve efficiency, existing methods primarily reduce redundancy by pruning…

Artificial Intelligence · Computer Science 2026-05-22 Bingjun Luo , Tony Wang , Chaoqi Chen , Xinpeng Ding

Understanding long video content is a complex endeavor that often relies on densely sampled frame captions or end-to-end feature selectors, yet these techniques commonly overlook the logical relationships between textual queries and visual…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Weiyu Guo , Ziyang Chen , Shaoguang Wang , Jianxiang He , Yijie Xu , Jinhui Ye , Ying Sun , Hui Xiong

Multimodal large language models (MLLMs) have enabled open-world visual understanding by injecting visual input as extra tokens into large language models (LLMs) as contexts. However, when the visual input changes from a single image to a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Xi Tang , Jihao Qiu , Lingxi Xie , Yunjie Tian , Jianbin Jiao , Qixiang Ye

Video question answering is a challenging task that requires understanding jointly the language input, the visual information in individual video frames, as well as the temporal information about the events occurring in the video. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 AJ Piergiovanni , Kairo Morton , Weicheng Kuo , Michael S. Ryoo , Anelia Angelova

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Chenyu Yang , Xuan Dong , Xizhou Zhu , Weijie Su , Jiahao Wang , Hao Tian , Zhe Chen , Wenhai Wang , Lewei Lu , Jifeng Dai

Current approaches for activity recognition often ignore constraints on computational resources: 1) they rely on extensive feature computation to obtain rich descriptors on all frames, and 2) they assume batch-mode access to the entire test…

Computer Vision and Pattern Recognition · Computer Science 2016-04-05 Yu-Chuan Su , Kristen Grauman

Encoding a sequence of observations is an essential task with many applications. The encoding can become highly efficient when the observations are generated by a dynamical system. A dynamical system imposes regularities on the observations…

Machine Learning · Statistics 2018-05-29 Arash Mehrjou , Friedrich Solowjow , Sebastian Trimpe , Bernhard Schölkopf

Rapid advances in Large Language Models (LLMs) have spurred demand for processing extended context sequences in contemporary applications. However, this progress faces two challenges: performance degradation due to sequence lengths…

Computation and Language · Computer Science 2025-10-10 Wei Wu , Zhuoshi Pan , Chao Wang , Liyi Chen , Yunchu Bai , Tianfu Wang , Kun Fu , Zheng Wang , Hui Xiong

We propose an efficient framework to compress massive video-frame features before feeding them into large multimodal models, thereby mitigating the severe token explosion arising from hour-long videos. Our design leverages a bidirectional…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Geewook Kim , Minjoon Seo

Recent advancements in large video-language models have revolutionized video understanding tasks. However, their efficiency is significantly constrained by processing high volumes of visual tokens. Existing token compression strategies…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Xiangchen Wang , Jinrui Zhang , Teng Wang , Haigang Zhang , Feng Zheng

Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Shuhong Zheng , Michael Oechsle , Erik Sandström , Marie-Julie Rakotosaona , Federico Tombari , Igor Gilitschenski

The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Peiran Wu , Zhuorui Yu , Yunze Liu , Chi-Hao Wu , Enmin Zhou , Junxiao Shen

While most modern video understanding models operate on short-range clips, real-world videos are often several minutes long with semantically consistent segments of variable length. A common approach to process long videos is applying a…

Computer Vision and Pattern Recognition · Computer Science 2023-09-22 Mohamed Afham , Satya Narayan Shukla , Omid Poursaeed , Pengchuan Zhang , Ashish Shah , Sernam Lim

Long-form video question answering (VQA) overwhelms current vision-language models (VLMs) because attention and key-value (KV) caches grow with runtime, forcing either expensive inference or near-sighted sliding windows. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Shrenik Patel , Daivik Patel

Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Zheyu Zhang , Ziqi Pang , Shixing Chen , Xiang Hao , Vimal Bhat , Yu-Xiong Wang