English
Related papers

Related papers: Should VLMs be Pre-trained with Image Data?

200 papers

The ratio of outlier parameters in language pre-training models and vision pre-training models differs significantly, making cross-modality (language and vision) inherently more challenging than cross-domain adaptation. As a result, many…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Yaxin Luo , Zhiqiang Shen

Large Language Model-based Vision-Language Models (LLM-based VLMs) have demonstrated impressive results in various vision-language understanding tasks. However, how well these VLMs can see image detail beyond the semantic level remains…

Computer Vision and Pattern Recognition · Computer Science 2024-08-08 Chenhui Gou , Abdulwahab Felemban , Faizan Farooq Khan , Deyao Zhu , Jianfei Cai , Hamid Rezatofighi , Mohamed Elhoseiny

While pretraining on large-scale image-text data from the Web has facilitated rapid progress on many vision-and-language (V&L) tasks, recent work has demonstrated that pretrained models lack "fine-grained" understanding, such as the ability…

Computation and Language · Computer Science 2023-05-15 Emanuele Bugliarello , Laurent Sartran , Aishwarya Agrawal , Lisa Anne Hendricks , Aida Nematzadeh

Multimodal Vision-Language Models (VLMs) enable powerful applications from their fused understanding of images and language, but many perform poorly on UI tasks due to the lack of UI training data. In this paper, we adapt a recipe for…

Human-Computer Interaction · Computer Science 2023-10-10 Yue Jiang , Eldon Schoop , Amanda Swearngin , Jeffrey Nichols

Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and…

Computation and Language · Computer Science 2021-04-22 Ozan Caglayan , Menekse Kuyu , Mustafa Sercan Amac , Pranava Madhyastha , Erkut Erdem , Aykut Erdem , Lucia Specia

Vision-language models (VLMs) have enabled strong zero-shot classification through image-text alignment. Yet, their purely visual inference capabilities remain under-explored. In this work, we conduct a comprehensive evaluation of both…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Illia Volkov , Nikita Kisel , Klara Janouskova , Jiri Matas

Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs. Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks. Despite the satisfying…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Zhifang Zhang , Yuwei Niu , Xin Liu , Beibei Li

State-of-the-art Vision-Language Models (VLMs) ground the vision and the language modality primarily via projecting the vision tokens from the encoder to language-like tokens, which are directly fed to the Large Language Model (LLM)…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Sivan Doveh , Shaked Perek , M. Jehanzeb Mirza , Wei Lin , Amit Alfassy , Assaf Arbelle , Shimon Ullman , Leonid Karlinsky

With the burgeoning amount of data of image-text pairs and diversity of Vision-and-Language (V\&L) tasks, scholars have introduced an abundance of deep learning models in this research domain. Furthermore, in recent years, transfer learning…

Computation and Language · Computer Science 2024-12-12 Thong Nguyen , Cong-Duy Nguyen , Xiaobao Wu , See-Kiong Ng , Anh Tuan Luu

Language model (LM) pre-training is useful in many language processing tasks. But can pre-trained LMs be further leveraged for more general machine learning problems? We propose an approach for using LMs to scaffold learning and…

Standard practice in pretraining multimodal models, such as vision-language models, is to rely on pairs of aligned inputs from both modalities, for example, aligned image-text pairs. However, such pairs can be difficult to obtain in…

Computation and Language · Computer Science 2022-11-02 Elad Segal , Ben Bogin , Jonathan Berant

Although pre-trained language models~(PLMs) have shown impressive performance by text-only self-supervised training, they are found lack of visual semantics or commonsense. Existing solutions often rely on explicit images for visual…

Computation and Language · Computer Science 2023-05-29 Hangyu Guo , Kun Zhou , Wayne Xin Zhao , Qinyu Zhang , Ji-Rong Wen

Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream of a language model. This allows text and image information to fully attend to one another within…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Moritz Böhle , Amélie Royer , Juliette Marrie , Edouard Grave , Patrick Pérez

In standard large vision-language models (LVLMs) pre-training, the model typically maximizes the joint probability of the caption conditioned on the image via next-token prediction (NTP); however, since only a small subset of caption tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Yangyi Chen , Hao Peng , Tong Zhang , Heng Ji

Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Junshan Hu , Jialiang Mao , Zhikang Liu , Zhongpu Xia , Peng Jia , Xianpeng Lang

Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves…

Computer Vision and Pattern Recognition · Computer Science 2022-05-02 Sibo Song , Jianqiang Wan , Zhibo Yang , Jun Tang , Wenqing Cheng , Xiang Bai , Cong Yao

We initiate the first empirical study on the use of MLP architectures for vision-and-language (VL) fusion. Through extensive experiments on 5 VL tasks and 5 robust VQA benchmarks, we find that: (i) Without pre-training, using MLPs for…

Computer Vision and Pattern Recognition · Computer Science 2021-12-09 Yixin Nie , Linjie Li , Zhe Gan , Shuohang Wang , Chenguang Zhu , Michael Zeng , Zicheng Liu , Mohit Bansal , Lijuan Wang

As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inherently constrained by challenges such as the need for…

Computer Vision and Pattern Recognition · Computer Science 2024-08-12 Dongsheng Wang , Jiequan Cui , Miaoge Li , Wang Lin , Bo Chen , Hanwang Zhang

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations…

Computer Vision and Pattern Recognition · Computer Science 2022-05-17 Zirui Wang , Jiahui Yu , Adams Wei Yu , Zihang Dai , Yulia Tsvetkov , Yuan Cao

This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs). Our approach employs a sequence of visual resamplers that capture visual details at various…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Ziyuan Huang , Kaixiang Ji , Biao Gong , Zhiwu Qing , Qinglong Zhang , Kecheng Zheng , Jian Wang , Jingdong Chen , Ming Yang