English
Related papers

Related papers: Diversifying Joint Vision-Language Tokenization Le…

200 papers

Audio-visual learning, aimed at exploiting the relationship between audio and visual modalities, has drawn considerable attention since deep learning started to be used successfully. Researchers tend to leverage these two modalities either…

Computer Vision and Pattern Recognition · Computer Science 2020-01-15 Hao Zhu , Mandi Luo , Rui Wang , Aihua Zheng , Ran He

Continual learning aims to train a model incrementally on a sequence of tasks without forgetting previous knowledge. Although continual learning has been widely studied in computer vision, its application to Vision+Language tasks is not…

Machine Learning · Computer Science 2024-01-23 Mavina Nikandrou , Lu Yu , Alessandro Suglia , Ioannis Konstas , Verena Rieser

Visual tokenizers are fundamental to image generation. They convert visual data into discrete tokens, enabling transformer-based models to excel at image generation. Despite their success, VQ-based tokenizers like VQGAN face significant…

Computer Vision and Pattern Recognition · Computer Science 2024-11-28 Zechen Bai , Jianxiong Gao , Ziteng Gao , Pichao Wang , Zheng Zhang , Tong He , Mike Zheng Shou

Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks. However, their utility is limited by their entanglement with respect to different visual attributes. For…

Computer Vision and Pattern Recognition · Computer Science 2023-11-14 James Oldfield , Christos Tzelepis , Yannis Panagakis , Mihalis A. Nicolaou , Ioannis Patras

We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the…

Computation and Language · Computer Science 2024-08-28 Shannon Zejiang Shen , Hunter Lang , Bailin Wang , Yoon Kim , David Sontag

Previous vision-language pre-training models mainly construct multi-modal inputs with tokens and objects (pixels) followed by performing cross-modality interaction between them. We argue that the input of only tokens and object features…

Computer Vision and Pattern Recognition · Computer Science 2022-09-15 Zejun Li , Zhihao Fan , Huaixiao Tou , Jingjing Chen , Zhongyu Wei , Xuanjing Huang

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Aarti Ghatkesar , Ganesh Venkatesh

Vision-language pre-training (VLP) on large-scale image-text pairs has recently witnessed rapid progress for learning cross-modal representations. Existing pre-training methods either directly concatenate image representation and text…

Computation and Language · Computer Science 2021-03-16 Chenliang Li , Ming Yan , Haiyang Xu , Fuli Luo , Wei Wang , Bin Bi , Songfang Huang

Multilingual (or cross-lingual) embeddings represent several languages in a unique vector space. Using a common embedding space enables for a shared semantic between words from different languages. In this paper, we propose to embed images…

Computer Vision and Pattern Recognition · Computer Science 2019-05-15 Maxime Portaz , Hicham Randrianarivo , Adrien Nivaggioli , Estelle Maudet , Christophe Servan , Sylvain Peyronnet

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Artificial Intelligence · Computer Science 2025-08-14 Zixian Guo , Ming Liu , Qilong Wang , Zhilong Ji , Jinfeng Bai , Lei Zhang , Wangmeng Zuo

Recently, maximizing mutual information has emerged as a powerful method for unsupervised graph representation learning. The existing methods are typically effective to capture information from the topology view but ignore the feature view.…

Machine Learning · Computer Science 2022-10-12 Xiaolong Fan , Maoguo Gong , Yue Wu , Hao Li

Hashing techniques have been applied broadly in retrieval tasks due to their low storage requirements and high speed of processing. Many hashing methods based on a single view have been extensively studied for information retrieval.…

Machine Learning · Computer Science 2020-01-07 Jun Yu , Xiao-Jun Wu , Josef Kittler

Speech and text are two major forms of human language. The research community has been focusing on mapping speech to text or vice versa for many years. However, in the field of language modeling, very little effort has been made to model…

Computation and Language · Computer Science 2023-10-16 Ju-Chieh Chou , Chung-Ming Chien , Wei-Ning Hsu , Karen Livescu , Arun Babu , Alexis Conneau , Alexei Baevski , Michael Auli

Visual Similarity plays an important role in many computer vision applications. Deep metric learning (DML) is a powerful framework for learning such similarities which not only generalize from training data to identically distributed test…

Computer Vision and Pattern Recognition · Computer Science 2020-09-11 Timo Milbich , Karsten Roth , Homanga Bharadhwaj , Samarth Sinha , Yoshua Bengio , Björn Ommer , Joseph Paul Cohen

Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to supervising VLAs with latent actions are fragmented and…

Robotics · Computer Science 2026-05-07 Yihan Lin , Haoyang Li , Yang Li , Haitao Shen , Yihan Zhao , Chao Shao , Jing Zhang

The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. The motivation is…

Computer Vision and Pattern Recognition · Computer Science 2018-04-16 Sandro Pezzelle , Ionut-Teodor Sorodoc , Raffaella Bernardi

Existing multi-view representation learning methods typically follow a specific-to-uniform pipeline, extracting latent features from each view and then fusing or aligning them to obtain the unified object representation. However, the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Ren Wang , Haoliang Sun , Yuling Ma , Xiaoming Xi , Yilong Yin

Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for many applications: 1) the lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this…

Computer Vision and Pattern Recognition · Computer Science 2018-08-03 Hsin-Ying Lee , Hung-Yu Tseng , Jia-Bin Huang , Maneesh Kumar Singh , Ming-Hsuan Yang

In this work, we present MoLang (a Motion-Language connecting model) for learning joint representation of human motion and language, leveraging both unpaired and paired datasets of motion and language modalities. To this end, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2022-10-28 Jihoon Kim , Youngjae Yu , Seungyoun Shin , Taehyun Byun , Sungjoon Choi

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Ziyao Wang , Chen Chen , Jingtao Li , Weiming Zhuang , Jiabo Huang , Ang Li , Lingjuan Lyu