English
Related papers

Related papers: CoME-VL: Scaling Complementary Multi-Encoder Visio…

200 papers

To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adjacent visual tokens.…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Yifan Li , Wentao Bao , Botao Ye , Zhen Tan , Tianlong Chen , Huan Liu , Yu Kong

Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject to several…

Computer Vision and Pattern Recognition · Computer Science 2024-04-11 Oğuzhan Fatih Kar , Alessio Tonioni , Petra Poklukar , Achin Kulshrestha , Amir Zamir , Federico Tombari

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Yuchen Liu , Yaoming Wang , Bowen Shi , Xiaopeng Zhang , Wenrui Dai , Chenglin Li , Hongkai Xiong , Qi Tian

In recent years, large-scale vision-language models (VLMs) have demonstrated remarkable performance on multimodal understanding and reasoning tasks. However, handling high-dimensional visual features often incurs substantial computational…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Xiaoyang Guo , Keze Wang

Recent advancements in multimodal fusion have witnessed the remarkable success of vision-language (VL) models, which excel in various multimodal applications such as image captioning and visual question answering. However, building VL…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Zhiwei Hao , Jianyuan Guo , Li Shen , Yong Luo , Han Hu , Yonggang Wen

Existing visual token compression methods for Multimodal Large Language Models (MLLMs) predominantly operate as post-encoder modules, limiting their potential for efficiency gains. To address this limitation, we propose LaCo (Layer-wise…

Computer Vision and Pattern Recognition · Computer Science 2025-07-04 Juntao Liu , Liqiang Niu , Wenchao Chen , Jie Zhou , Fandong Meng

We present Florence-VL, a new family of multimodal large language models (MLLMs) with enriched visual representations produced by Florence-2, a generative vision foundation model. Unlike the widely used CLIP-style vision transformer trained…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Jiuhai Chen , Jianwei Yang , Haiping Wu , Dianqi Li , Jianfeng Gao , Tianyi Zhou , Bin Xiao

Recent research has shown that CLIP models struggle with visual reasoning tasks that require grounding compositionality, understanding spatial relationships, or capturing fine-grained details. One natural hypothesis is that the CLIP vision…

Machine Learning · Computer Science 2025-07-23 Siting Li , Pang Wei Koh , Simon Shaolei Du

Current multimodal models, aimed at solving Vision and Language (V+L) tasks, predominantly repurpose Vision Encoders (VE) as feature extractors. While many VEs -- of different architectures, trained on different data and objectives -- are…

Computer Vision and Pattern Recognition · Computer Science 2023-06-09 Gregor Geigle , Chen Cecilia Liu , Jonas Pfeiffer , Iryna Gurevych

Vision-Language Models (VLMs) are a new family of models that align image content with natural language. Existing approaches typically fuse either (a) early: by mixing tokens/features inside the encoders, or (b) late: by comparing pooled…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Benjamin Fein-Ashley , Jacob Fein-Ashley

Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. However, the vision encoders set a strong inductive bias in abstracting…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Haiwen Diao , Yufeng Cui , Xiaotong Li , Yueze Wang , Huchuan Lu , Xinlong Wang

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Bangzheng Li , Fei Wang , Wenxuan Zhou , Nan Xu , Ben Zhou , Sheng Zhang , Hoifung Poon , Muhao Chen

In this paper, we propose Conceptual Codebook Learning (CoCoLe), a novel fine-tuning method for vision-language models (VLMs) to address the challenge of improving the generalization capability of VLMs while fine-tuning them on downstream…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Yi Zhang , Ke Yu , Siqi Wu , Zhihai He

Vision-language models, such as CLIP, have achieved significant success in aligning visual and textual representations, becoming essential components of many multi-modal large language models (MLLMs) like LLaVA and OpenFlamingo. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Shizhan Gong , Yankai Jiang , Qi Dou , Farzan Farnia

Vision-and-language models (VLMs) have been increasingly explored in the medical domain, particularly following the success of CLIP in general domain. However, unlike the relatively straightforward pairing of 2D images and text, curating…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Ziyang Zhang , Yang Yu , Xulei Yang , Si Yong Yeo

Vision-language models (VLMs) have demonstrated strong cross-modal capabilities, yet most work remains limited to 2D data and assumes binary supervision (i.e., positive vs. negative pairs), overlooking the continuous and structured…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Ailar Mahdizadeh , Puria Azadi Moghadam , Xiangteng He , Shahriar Mirabbasi , Panos Nasiopoulos , Leonid Sigal

Vision-language models (VLMs) benefit from multiple vision encoders, but naively stacking them yields diminishing returns while multiplying inference costs. We propose SCOPE, a Mixture-of-Encoders (MoEnc) framework that dynamically selects…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Tianyu Zhang , Suyuchen Wang , Chao Wang , Juan Rodriguez , Ahmed Masry , Xiangru Jian , Yoshua Bengio , Perouz Taslakian

The ability to accurately interpret complex visual information is a crucial topic of multimodal large language models (MLLMs). Recent work indicates that enhanced visual perception significantly reduces hallucinations and improves…

Recent advancements in Multimodal Large Language Models (MLLMs) have revolutionized the field of vision-language understanding by integrating visual perception capabilities into Large Language Models (LLMs). The prevailing trend in this…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Sirnam Swetha , Jinyu Yang , Tal Neiman , Mamshad Nayeem Rizve , Son Tran , Benjamin Yao , Trishul Chilimbi , Mubarak Shah

Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Long Cui , Weiyun Wang , Jie Shao , Zichen Wen , Gen Luo , Linfeng Zhang , Yanting Zhang , Yu Qiao , Wenhai Wang