English
Related papers

Related papers: Autoregressive Pre-Training on Pixels and Texts

200 papers

Recent advances in image tokenizers, such as VQ-VAE, have enabled text-to-image generation using auto-regressive methods, similar to language modeling. However, these methods have yet to leverage pre-trained language models, despite their…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Yuhui Zhang , Brandon McKinzie , Zhe Gan , Vaishaal Shankar , Alexander Toshev

Pre-trained large language models have recently achieved ground-breaking performance in a wide variety of language understanding tasks. However, the same model can not be applied to multimodal behavior understanding tasks (e.g., video…

Computation and Language · Computer Science 2023-03-30 Md Kamrul Hasan , Md Saiful Islam , Sangwu Lee , Wasifur Rahman , Iftekhar Naim , Mohammed Ibrahim Khan , Ehsan Hoque

Many self-supervised learning methods are pre-trained on the well-curated ImageNet-1K dataset. In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Bingchen Zhao , Quan Cui , Hao Wu , Osamu Yoshie , Cheng Yang , Oisin Mac Aodha

Integrating visual features has been proved useful for natural language understanding tasks. Nevertheless, in most existing multimodal language models, the alignment of visual and textual data is expensive. In this paper, we propose a novel…

Computation and Language · Computer Science 2020-08-14 Lisai Zhang , Qingcai Chen , Dongfang Li , Buzhou Tang

Since the emergence of Vision Transformer (ViT), it has been widely used in generative language model and generative visual model. Especially in the current state-of-art open source multimodal models, ViT obtained by CLIP or SigLIP method…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Haun Leung , ZiNan Wang

Significant progress has been made on visual captioning, largely relying on pre-trained features and later fixed object detectors that serve as rich inputs to auto-regressive models. A key limitation of such methods, however, is that the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-09 Chia-Wen Kuo , Zsolt Kira

Visual language models (VLMs) rapidly progressed with the recent success of large language models. There have been growing efforts on visual instruction tuning to extend the LLM with visual inputs, but lacks an in-depth study of the visual…

Computer Vision and Pattern Recognition · Computer Science 2024-05-20 Ji Lin , Hongxu Yin , Wei Ping , Yao Lu , Pavlo Molchanov , Andrew Tao , Huizi Mao , Jan Kautz , Mohammad Shoeybi , Song Han

We present a novel visual instruction tuning strategy to improve the zero-shot task generalization of multimodal large language models by building a firm text-only knowledge base. Existing work lacks sufficient experimentation on the…

Computation and Language · Computer Science 2025-07-01 Jianhong Tu , Zhuohao Ni , Nicholas Crispino , Zihao Yu , Michael Bendersky , Beliz Gunel , Ruoxi Jia , Xin Liu , Lingjuan Lyu , Dawn Song , Chenguang Wang

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…

Computation and Language · Computer Science 2023-02-28 Weizhi Wang , Li Dong , Hao Cheng , Haoyu Song , Xiaodong Liu , Xifeng Yan , Jianfeng Gao , Furu Wei

We introduce and demonstrate how to effectively train multilingual machine translation models with pixel representations. We experiment with two different data settings with a variety of language and script coverage, demonstrating improved…

Computation and Language · Computer Science 2023-10-25 Elizabeth Salesky , Neha Verma , Philipp Koehn , Matt Post

Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Xuelin Zhu , Jiuxin Cao , Jian liu , Dongqi Tang , Furong Xu , Weijia Liu , Jiawei Ge , Bo Liu , Qingpei Guo , Tianyi Zhang

Video-Language Pre-training models have recently significantly improved various multi-modal downstream tasks. Previous dominant works mainly adopt contrastive learning to achieve global feature alignment across modalities. However, the…

Computer Vision and Pattern Recognition · Computer Science 2023-01-19 Fan Ma , Xiaojie Jin , Heng Wang , Jingjia Huang , Linchao Zhu , Jiashi Feng , Yi Yang

Pretrained vision-and-language BERTs aim to learn representations that combine information from both modalities. We propose a diagnostic method based on cross-modal input ablation to assess the extent to which these models actually…

Computation and Language · Computer Science 2021-09-10 Stella Frank , Emanuele Bugliarello , Desmond Elliott

In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. The unified view helps us to better…

Computation and Language · Computer Science 2021-04-08 Zewen Chi , Li Dong , Furu Wei , Nan Yang , Saksham Singhal , Wenhui Wang , Xia Song , Xian-Ling Mao , Heyan Huang , Ming Zhou

Visual grounding of Language aims at enriching textual representations of language with multiple sources of visual knowledge such as images and videos. Although visual grounding is an area of intense research, inter-lingual aspects of…

Computation and Language · Computer Science 2022-11-22 Wafaa Mohammed , Hassan Shahmohammadi , Hendrik P. A. Lensch , R. Harald Baayen

Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which…

Computer Vision and Pattern Recognition · Computer Science 2021-11-16 Lewei Yao , Runhui Huang , Lu Hou , Guansong Lu , Minzhe Niu , Hang Xu , Xiaodan Liang , Zhenguo Li , Xin Jiang , Chunjing Xu

Connecting text and visual modalities plays an essential role in generative intelligence. For this reason, inspired by the success of large language models, significant research efforts are being devoted to the development of Multimodal…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Davide Caffagni , Federico Cocchi , Luca Barsellotti , Nicholas Moratelli , Sara Sarto , Lorenzo Baraldi , Lorenzo Baraldi , Marcella Cornia , Rita Cucchiara

Pretrained visual-language models have made significant advancements in multimodal tasks, including image-text retrieval. However, a major challenge in image-text matching lies in language bias, where models predominantly rely on language…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Jiwan Chung , Seungwon Lim , Sangkyu Lee , Youngjae Yu

Vision-and-Language (V+L) pre-training models have achieved tremendous success in recent years on various multi-modal benchmarks. However, the majority of existing models require pre-training on a large set of parallel image-text data,…

Computer Vision and Pattern Recognition · Computer Science 2022-03-02 Mingyang Zhou , Licheng Yu , Amanpreet Singh , Mengjiao Wang , Zhou Yu , Ning Zhang

Multi-modal document pre-trained models have proven to be very effective in a variety of visually-rich document understanding (VrDU) tasks. Though existing document pre-trained models have achieved excellent performance on standard…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Chuwei Luo , Guozhi Tang , Qi Zheng , Cong Yao , Lianwen Jin , Chenliang Li , Yang Xue , Luo Si