English
Related papers

Related papers: Anisotropic Modality Align

200 papers

Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Xiaomin Yu , Yi Xin , Yuhui Zhang , Wenjie Zhang , Chonghan Liu , Hanzhen Zhao , Chen Liu , Xiaoxing Hu , Ziyue Qiao , Hao Tang , Xiaobin Hu , Chengwei Qin , Hui Xiong , Yu Qiao , Shuicheng Yan

We present modality gap, an intriguing geometric phenomenon of the representation space of multi-modal models. Specifically, we show that different data modalities (e.g. images and text) are embedded at arm's length in their shared…

Computation and Language · Computer Science 2022-10-21 Weixin Liang , Yuhui Zhang , Yongchan Kwon , Serena Yeung , James Zou

Multimodal contrastive learning (MCL) aims to embed data from different modalities in a shared embedding space. However, empirical evidence shows that representations from different modalities occupy completely separate regions of embedding…

Machine Learning · Computer Science 2025-10-09 Lingjie Yi , Raphael Douady , Chao Chen

Multimodal learning has recently gained significant popularity, demonstrating impressive performance across various zero-shot classification tasks and a range of perceptive and generative applications. Models such as Contrastive…

Machine Learning · Computer Science 2026-02-16 Can Yaras , Siyi Chen , Peng Wang , Qing Qu

We explore Multimodal Large Language Models (MLLMs), which integrate LLMs like GPT-4 to handle multimodal data, including text, images, audio, and more. MLLMs demonstrate capabilities such as generating image captions and answering…

Computation and Language · Computer Science 2025-01-09 Shezheng Song , Xiaopeng Li , Shasha Li , Shan Zhao , Jie Yu , Jun Ma , Xiaoguang Mao , Weimin Zhang

In multimodal learning, CLIP has emerged as the de-facto approach for mapping different modalities into a shared latent space by bringing semantically similar representations closer while pushing apart dissimilar ones. However, CLIP-based…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Eleonora Grassucci , Giordano Cicchetti , Danilo Comminiello

Multimodal representation learning aims to construct a shared embedding space in which heterogeneous modalities are semantically aligned. Despite strong empirical results, InfoNCE-based objectives introduce inherent conflicts that yield…

Machine Learning · Computer Science 2026-02-11 Wenzhe Yin , Pan Zhou , Zehao Xiao , Jie Liu , Shujian Yu , Jan-Jakob Sonke , Efstratios Gavves

Multimodal representation learning produces high-dimensional embeddings that align diverse modalities in a shared latent space. While this enables strong generalization, it also introduces scalability challenges, both in terms of storage…

Machine Learning · Computer Science 2025-09-30 Eleonora Grassucci , Giordano Cicchetti , Aurelio Uncini , Danilo Comminiello

Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data, requiring substantial human effort to construct multi-way aligned datasets and thereby…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Yan Li , Yunlong Deng , Yuewen Sun , Gongxu Luo , Kun Zhang , Guangyi Chen

Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the modality gap. This gap limits tasks requiring cross-modal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Hongyuan Liu , Qinli Yang , Wen Li , Zhong Zhang , Jiaming Liu , Wei Han , Zhili Qin , Jinxia Guo , Junming Shao

Learning joint embedding space for various modalities is of vital importance for multimodal fusion. Mainstream modality fusion approaches fail to achieve this goal, leaving a modality gap which heavily affects cross-modal fusion. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-12-11 Sijie Mai , Haifeng Hu , Songlong Xing

Multimodal representation learning is fundamentally about transforming incomparable modalities into comparable representations. While prior research primarily focused on explicitly aligning these representations through targeted learning…

Machine Learning · Computer Science 2025-06-16 Megan Tjandrasuwita , Chanakya Ekbote , Liu Ziyin , Paul Pu Liang

Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Giordano Cicchetti , Eleonora Grassucci , Luigi Sigillo , Danilo Comminiello

Combining multimodal data is a key issue in a wide range of machine learning tasks, including many remote sensing problems. In Earth observation, early multimodal data fusion methods were based on specific neural network architectures and…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Romain Thoreau , Jessie Levillain , Dawa Derksen

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 François Role , Sébastien Meyer , Victor Amblard

Different machine learning models can represent the same underlying concept in different ways. This variability is particularly valuable for in-the-wild multimodal retrieval, where the objective is to identify the corresponding…

Information Retrieval · Computer Science 2025-06-11 Fan Xu , Luis A. Leiva

Multimodal representation learning aims to capture both shared and complementary semantic information across multiple modalities. However, the intrinsic heterogeneity of diverse modalities presents substantial challenges to achieve…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Chengxuan Qian , Shuo Xing , Shawn Li , Yue Zhao , Zhengzhong Tu

Contrastive loss has been increasingly used in learning representations from multiple modalities. In the limit, the nature of the contrastive loss encourages modalities to exactly match each other in the latent space. Yet it remains an open…

Machine Learning · Computer Science 2023-03-13 Qian Jiang , Changyou Chen , Han Zhao , Liqun Chen , Qing Ping , Son Dinh Tran , Yi Xu , Belinda Zeng , Trishul Chilimbi

Multimodal representation learning harmonizes distinct modalities by aligning them into a unified latent space. Recent research generalizes traditional cross-modal alignment to produce enhanced multimodal synergy but requires all modalities…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Xiaohao Liu , Xiaobo Xia , Jiaheng Wei , Shuo Yang , Xiu Su , See-Kiong Ng , Tat-Seng Chua

Foundation models learn highly transferable representations through large-scale pretraining on diverse data. An increasing body of research indicates that these representations exhibit a remarkable degree of similarity across architectures…

Artificial Intelligence · Computer Science 2025-10-08 Jianglin Lu , Hailing Wang , Yi Xu , Yizhou Wang , Kuo Yang , Yun Fu
‹ Prev 1 2 3 10 Next ›