English
Related papers

Related papers: Optimizing Vision-Language Interactions Through De…

200 papers

Pretrained vision-language models (VLMs), such as CLIP, achieve remarkable zero-shot performance, yet their downstream potential hinges on effective fine-tuning. Most adaptation methods typically focus on refining representation from…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Liang Chen , Ghazi Shazan Ahmad , Tianjun Yao , Lingqiao Liu , Zhiqiang Shen

Multimodal language generation, which leverages the synergy of language and vision, is a rapidly expanding field. However, existing vision-language models face challenges in tasks that require complex linguistic understanding. To address…

Computation and Language · Computer Science 2023-12-20 Jiwan Chung , Youngjae Yu

Vision-language models (VLMs) are often deployed on text-only inputs, although they are trained with images. We find that removing the vision modality causes large drops in accuracy and severe miscalibration, and the model does not behave…

Computation and Language · Computer Science 2026-05-14 Mingyeong Kim , Jungwon Choi , Chaeyun Jang , Juho Lee

Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Dawei Yan , Pengcheng Li , Yang Li , Hao Chen , Qingguo Chen , Weihua Luo , Wei Dong , Qingsen Yan , Haokui Zhang , Chunhua Shen

Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to loss of fine-grained visual information. Recently the proposal of ''thinking with images''…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Junfei Wu , Jian Guan , Qiang Liu , Shu Wu , Liang Wang , Wei Wu , Tieniu Tan

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Juncheng Yang , Zuchao Li , Shuai Xie , Weiping Zhu , Wei Yu , Shijun Li

While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pretraining (VDEP), a hybrid autoregressive training paradigm…

Computer Vision and Pattern Recognition · Computer Science 2025-02-14 Mingxiao Li , Fang Qu , Zhanpeng Chen , Na Su , Zhizhou Zhong , Ziyang Chen , Nan Du , Xiaolong Li

Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from a performance trade-off between these capabilities. We…

Large Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics. These visual tokens often outnumber their textual counterparts by a large margin, leading to substantial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Rui Xu , Yunke Wang , Yong Luo , Bo Du

Vision-language models (VLMs) have exhibited remarkable generalization capabilities, and prompt learning for VLMs has attracted great attention for the ability to adapt pre-trained VLMs to specific downstream tasks. However, existing…

Machine Learning · Computer Science 2025-01-15 Song-Lin Lv , Yu-Yang Chen , Zhi Zhou , Ming Yang , Lan-Zhe Guo

The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency…

Computer Vision and Pattern Recognition · Computer Science 2025-04-28 Yasmine Omri , Parth Shroff , Thierry Tambe

Vision-language models (VLMs) serve as general-purpose end-to-end models in autonomous driving, performing subtasks such as prediction, planning, and perception through question-and-answer interactions. However, most existing methods rely…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Enming Zhang , Xingyuan Dai , Min Huang , Yisheng Lv , Qinghai Miao

Despite the significant advancements represented by Vision-Language Models (VLMs), current architectures often exhibit limitations in retaining fine-grained visual information, leading to coarse-grained multimodal comprehension. We…

While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine-grained perception tasks that require identifying tiny objects or discerning subtle…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Jilong Zhu , Yang Feng

Video-based dialog task is a challenging multimodal learning task that has received increasing attention over the past few years with state-of-the-art obtaining new performance records. This progress is largely powered by the adaptation of…

Computer Vision and Pattern Recognition · Computer Science 2022-10-27 Huda Alamri , Anthony Bilic , Michael Hu , Apoorva Beedu , Irfan Essa

Vision-Language Models (VLMs) represent a significant breakthrough in artificial intelligence by integrating visual and textual modalities to achieve impressive zero-shot capabilities. However, VLMs are susceptible to catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Haoyuan Gao , Zicong Zhang , Yuqi Wei , Linglan Zhao , Guilin Li , Yexin Li , Bo Wang , Linghe Kong , Weiran Huang

Currently, vision encoder models like Vision Transformers (ViTs) typically excel at image recognition tasks but cannot simultaneously support text recognition like human visual recognition. To address this limitation, we propose UNIT, a…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Yi Zhu , Yanpeng Zhou , Chunwei Wang , Yang Cao , Jianhua Han , Lu Hou , Hang Xu

Multimodal large language models (MLLMs) require a nuanced interpretation of complex image information, typically leveraging a vision encoder to perceive various visual scenarios. However, relying solely on a single vision encoder to handle…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Xin He , Xumeng Han , Longhui Wei , Lingxi Xie , Qi Tian

Multimodal large language models (MLLMs) have significantly advanced the integration of visual and textual understanding. However, their ability to generate code from multimodal inputs remains limited. In this work, we introduce VisCodex, a…

Computation and Language · Computer Science 2025-08-14 Lingjie Jiang , Shaohan Huang , Xun Wu , Yixia Li , Dongdong Zhang , Furu Wei

The recent advent of Large Language Models (LLMs) has ushered sophisticated reasoning capabilities into the realm of video through Video Large Language Models (VideoLLMs). However, VideoLLMs currently rely on a single vision encoder for all…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Jihoon Chung , Tyler Zhu , Max Gonzalez Saez-Diez , Juan Carlos Niebles , Honglu Zhou , Olga Russakovsky