English
Related papers

Related papers: Training Vision-Language Models with Less Bimodal …

200 papers

In the field of multi-modal language models, the majority of methods are built on an architecture similar to LLaVA. These models use a single-layer ViT feature as a visual prompt, directly feeding it into the language models alongside…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Kaibing Chen , Dong Shen , Hanwen Zhong , Huasong Zhong , Kui Xia , Di Xu , Wei Yuan , Yifei Hu , Bin Wen , Tianke Zhang , Changyi Liu , Dewen Fan , Huihui Xiao , Jiahong Wu , Fan Yang , Size Li , Di Zhang

NLP models today strive for supporting multiple languages and modalities, improving accessibility for diverse users. In this paper, we evaluate their multilingual, multimodal capabilities by testing on a visual reasoning task. We observe…

Computation and Language · Computer Science 2025-02-11 Yueqi Song , Simran Khanuja , Graham Neubig

Large-scale pre-training and instruction tuning have been successful at creating general-purpose language models with broad competence. However, building general-purpose vision-language models is challenging due to the rich input…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Wenliang Dai , Junnan Li , Dongxu Li , Anthony Meng Huat Tiong , Junqi Zhao , Weisheng Wang , Boyang Li , Pascale Fung , Steven Hoi

Multilingual large language models achieve impressive cross-lingual performance despite largely monolingual pretraining. While bilingual data in pretraining corpora is widely believed to enable these abilities, details of its contributions…

Computation and Language · Computer Science 2026-01-26 Jiandong Shao , Raphael Tang , Crystina Zhang , Karin Sevegnani , Pontus Stenetorp , Jianfei Yang , Yao Lu

Vision-language models (VLMs) are increasingly attractive for multimodal quality assessment, but their default reliance on autoregressive text generation and dynamic visual processing is poorly matched to scalar regression under strict…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 William Leach , Ru He , Sizhuo Ma , Yizhen Jia , Min Cao , Jian Wang , Rick Cao

In many machine learning scenarios, supervision by gold labels is not available and consequently neural models cannot be trained directly by maximum likelihood estimation (MLE). In a weak supervision scenario, metric-augmented objectives…

Computation and Language · Computer Science 2019-07-10 Laura Jehl , Carolin Lawrence , Stefan Riezler

The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models remains opaque. We provide empirical clarity through…

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

State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Amanpreet Singh , Ronghang Hu , Vedanuj Goswami , Guillaume Couairon , Wojciech Galuba , Marcus Rohrbach , Douwe Kiela

Vision-language-action models (VLAs) trained on large-scale robotic datasets have demonstrated strong performance on manipulation tasks, including bimanual tasks. However, because most public datasets focus on single-arm demonstrations,…

Robotics · Computer Science 2026-02-24 Hokyun Im , Euijin Jeong , Andrey Kolobov , Jianlong Fu , Youngwoon Lee

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Lijie Zhou

This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-16 Po-Yao Huang , Mandela Patrick , Junjie Hu , Graham Neubig , Florian Metze , Alexander Hauptmann

Contrastive Language-Image Pre-training (CLIP) has demonstrated strong generalization across a wide range of visual tasks by leveraging large-scale English-image pairs. However, its extension to low-resource languages remains limited due to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Dahyun Chung , Donghyun Shin , Yujin Sung , Seunggi Moon , Jinwoo Jeon , Byung-Jun Lee

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

Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…

Computation and Language · Computer Science 2021-09-07 Yonatan Bitton , Gabriel Stanovsky , Michael Elhadad , Roy Schwartz

Text-rich images, where text serves as the central visual element guiding the overall understanding, are prevalent in real-world applications, such as presentation slides, scanned documents, and webpage snapshots. Tasks involving multiple…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Mengzhao Jia , Wenhao Yu , Kaixin Ma , Tianqing Fang , Zhihan Zhang , Siru Ouyang , Hongming Zhang , Dong Yu , Meng Jiang

Unified Multimodal Models (UMMs) are often constrained by the pre-training of their $\textbf{visual generation components}$, which typically relies on inefficient paradigms and scarce, high-quality text-image paired data. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Peng Sun , Jun Xie , Tao Lin

Foundation models have demonstrated remarkable performance across modalities such as language and vision. However, model reuse across distinct modalities (e.g., text and vision) remains limited due to the difficulty of aligning internal…

Machine Learning · Computer Science 2025-05-20 Ali Gholamzadeh , Noor Sajid

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Chao Jia , Yinfei Yang , Ye Xia , Yi-Ting Chen , Zarana Parekh , Hieu Pham , Quoc V. Le , Yunhsuan Sung , Zhen Li , Tom Duerig

Vision-Language Models (VLMs) excel in integrating visual and textual information for vision-centric tasks, but their handling of inconsistencies between modalities is underexplored. We investigate VLMs' modality preferences when faced with…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Ailin Deng , Tri Cao , Zhirui Chen , Bryan Hooi
‹ Prev 1 4 5 6 7 8 10 Next ›