English
Related papers

Related papers: Global Context Compression with Interleaved Vision…

200 papers

The computational and memory overheads associated with expanding the context window of LLMs severely limit their scalability. A noteworthy solution is vision-text compression (VTC), exemplified by frameworks like DeepSeek-OCR and Glyph,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Hongbo Zhao , Meng Wang , Fei Zhu , Wenzhuo Liu , Bolin Ni , Fanhu Zeng , Gaofeng Meng , Zhaoxiang Zhang

Large vision-language models (LVLMs) excel at visual understanding, but face efficiency challenges due to quadratic complexity in processing long multi-modal contexts. While token compression can reduce computational costs, existing…

Computer Vision and Pattern Recognition · Computer Science 2026-01-14 Xuyang Liu , Ziming Wang , Junjie Chen , Yuhang Han , Yingyao Wang , Jiale Yuan , Jun Song , Siteng Huang , Honggang Chen

The quadratic complexity of the attention module makes it gradually become the bulk of compute in Transformer-based LLMs during generation. Moreover, the excessive key-value cache that arises when dealing with long inputs also brings severe…

Computation and Language · Computer Science 2023-10-17 Siyu Ren , Qi Jia , Kenny Q. Zhu

This paper provides a simplification on OpenVision's architecture and loss design for enhancing its training efficiency. Following the prior vision-language pretraining works CapPa and AIMv2, as well as modern multimodal designs like LLaVA,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Yanqing Liu , Xianhang Li , Letian Zhang , Zirui Wang , Zeyu Zheng , Yuyin Zhou , Cihang Xie

Large Multimodal Models (LMMs) often face a modality representation gap during pretraining: while language embeddings remain stable, visual representations are highly sensitive to contextual noise (e.g., background clutter). To address this…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Yin Xie , Kaicheng Yang , Peirou Liang , Xiang An , Yongle Zhao , Yumeng Wang , Ziyong Feng , Roy Miles , Ismail Elezi , Jiankang Deng

The cost of deploying vision transformers increasingly represents a barrier to wider industrial adoption. Existing compression techniques require additional end-to-end fine-tuning or incur a significant drawback to energy efficiency, making…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Leonidas Gee , Wing Yan Li , Viktoriia Sharmanska , Novi Quadrianto

Training models with longer in-context lengths is a significant challenge for multimodal model due to substantial GPU memory and computational costs. This exploratory study does not present state-of-the-art models; rather, it introduces an…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Alex Jinpeng Wang , Linjie Li , Yiqi Lin , Min Li , Lijuan Wang , Mike Zheng Shou

Video instance segmentation (VIS) aims at classifying, segmenting and tracking object instances in video sequences. Recent transformer-based neural networks have demonstrated their powerful capability of modeling spatio-temporal…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Xiang Li , Jinglu Wang , Xiaohao Xu , Bhiksha Raj , Yan Lu

Visual instruction tuning aims to enable large language models to comprehend the visual world, with a pivotal challenge lying in establishing an effective vision-to-language projection. However, existing methods often grapple with the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Bonan li , Zicheng Zhang , Songhua Liu , Weihao Yu , Xinchao Wang

Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in learning comprehensive and compositional representations from…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Neha Kalibhat , Priyatham Kattakinda , Sumit Nawathe , Arman Zarei , Nikita Seleznev , Samuel Sharpe , Senthil Kumar , Soheil Feizi

Vision-Language Models (VLMs) have achieved remarkable success in various multi-modal tasks, but they are often bottlenecked by the limited context window and high computational cost of processing high-resolution image inputs and videos.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Xubing Ye , Yukang Gan , Xiaoke Huang , Yixiao Ge , Yansong Tang

Modern computer vision pipelines handle large images in one of two sub-optimal ways: down-sampling or cropping. These two methods incur significant losses in the amount of information and context present in an image. There are many…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Ritwik Gupta , Shufan Li , Tyler Zhu , Jitendra Malik , Trevor Darrell , Karttikeya Mangalam

Multi-modal retrieval becomes increasingly popular in practice. However, the existing retrievers are mostly text-oriented, which lack the capability to process visual information. Despite the presence of vision-language models like CLIP,…

Information Retrieval · Computer Science 2024-06-07 Junjie Zhou , Zheng Liu , Shitao Xiao , Bo Zhao , Yongping Xiong

In-context image generation models such as FLUX.2 take a text prompt and an optional reference image as visual conditioning for the output. Internally, all three inputs -- text, reference image, and the noise tokens -- are concatenated and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Chris Ge , Rohit Gandikota , Antonio Torralba , Tamar Rott Shaham

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…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Ce Zhang , Kaixin Ma , Tianqing Fang , Wenhao Yu , Hongming Zhang , Zhisong Zhang , Haitao Mi , Dong Yu

With the advancement of large-scale language modeling techniques, large multimodal models combining visual encoders with large language models have demonstrated exceptional performance in various visual tasks. Most of the current…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Yi Chen , Jian Xu , Xu-Yao Zhang , Wen-Zhuo Liu , Yang-Yang Liu , Cheng-Lin Liu

Recent advances in learned image compression (LIC) have achieved remarkable performance improvements over traditional codecs. Notably, the MLIC series-LICs equipped with multi-reference entropy models-have substantially surpassed…

Image and Video Processing · Electrical Eng. & Systems 2026-02-26 Wei Jiang , Yongqi Zhai , Jiayu Yang , Feng Gao , Ronggang Wang

Recent vision-centric approaches have made significant strides in long-context modeling. Represented by DeepSeek-OCR, these models encode rendered text into continuous vision tokens, achieving high compression rates without sacrificing…

Machine Learning · Computer Science 2026-02-04 Shuxin Zhuang , Zi Liang , Runsheng Yu , Hongzong Li , Rong Feng , Shiqin Tang , Youzhi Zhang

Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Dingchen Yang , Bowen Cao , Anran Zhang , Weibo Gu , Winston Hu , Guang Chen

In this work, we provide a thorough investigation of gist-based context compression methods to improve long-context processing in large language models. We focus on two key questions: (1) How well can these methods replace full attention…

Computation and Language · Computer Science 2024-12-24 Chenlong Deng , Zhisong Zhang , Kelong Mao , Shuaiyi Li , Xinting Huang , Dong Yu , Zhicheng Dou