English
Related papers

Related papers: e5-omni: Explicit Cross-modal Alignment for Omni-m…

200 papers

The success of vision-language models is primarily attributed to effective alignment across modalities such as vision and language. However, modality gaps persist in existing alignment algorithms and appear necessary for human perception as…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Hanqi Yan , Xiangxiang Cui , Lu Yin , Jindong Gu , Paul Pu Liang , Yulan He , Yifei Wang

Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Feng Han , Zhixiong Zhang , Zheming Liang , Yibin Wang , Jiaqi Wang

Research on multi-modal learning dominantly aligns the modalities in a unified space at training, and only a single one is taken for prediction at inference. However, for a real machine, e.g., a robot, sensors could be added or removed at…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Yuanhuiyi Lyu , Xu Zheng , Dahun Kim , Lin Wang

We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations. We find that such training enables Context Unrolling, where the model explicitly…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Ceyuan Yang , Zhijie Lin , Yang Zhao , Fei Xiao , Hao He , Qi Zhao , Chaorui Deng , Kunchang Li , Zihan Ding , Yuwei Guo , Fuyun Wang , Fangqi Zhu , Xiaonan Nie , Shenhan Zhu , Shanchuan Lin , Hongsheng Li , Weilin Huang , Guang Shi , Haoqi Fan

Due to the high stakes in medical decision-making, there is a compelling demand for interpretable deep learning methods in medical image analysis. Concept Bottleneck Models (CBM) have emerged as an active interpretable framework…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Yibo Gao , Zheyao Gao , Xin Gao , Yuanye Liu , Bomin Wang , Xiahai Zhuang

Multimodal learning systems often encounter challenges related to modality imbalance, where a dominant modality may overshadow others, thereby hindering the learning of weak modalities. Conventional approaches often force weak modalities to…

Machine Learning · Computer Science 2025-10-27 Baoquan Gong , Xiyuan Gao , Pengfei Zhu , Qinghua Hu , Bing Cao

Recent multimodal systems often rely on separate expert modality encoders which cause linearly scaling complexity and computational overhead with added modalities. While unified Omni-models address this via Mixture-of-Expert (MoE)…

Multimedia · Computer Science 2026-03-09 Kin Wai Lau , Yasar Abbas Ur Rehman , Lai-Man Po , Pedro Porto Buarque de Gusmão

As the real propagation environment becomes in creasingly complex and dynamic, millimeter wave beam prediction faces huge challenges. However, the powerful cross modal representation capability of vision-language model (VLM) provides a…

Signal Processing · Electrical Eng. & Systems 2025-08-18 Ji Wang , Bin Tang , Jian Xiao , Qimei Cui , Xingwang Li , Tony Q. S. Quek

Multimodal embeddings aim to enrich the semantic information in neural representations of language compared to text-only models. While different embeddings exhibit different applicability and performance on downstream tasks, little is known…

Computation and Language · Computer Science 2023-06-06 Aleksey Tikhonov , Lisa Bylinina , Denis Paperno

Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Ali Abdollah , Amirmohammad Izadi , Armin Saghafian , Reza Vahidimajd , Mohammad Mozafari , Amirreza Mirzaei , Mohammadmahdi Samiei , Mahdieh Soleymani Baghshah

Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Nikolaos-Antonios Ypsilantis , Kaifeng Chen , André Araujo , Ondřej Chum

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

Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like CLIP align…

Computation and Language · Computer Science 2025-10-20 Qiyu Wu , Shuyang Cui , Satoshi Hayakawa , Wei-Yao Wang , Hiromi Wakaki , Yuki Mitsufuji

Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Zhenxiang Lin , Maryam Haghighat , Will Browne , Dimity Miller

Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidate pairs. However, these methods often struggle to capture…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Tiancheng Gu , Kaicheng Yang , Kaichen Zhang , Xiang An , Ziyong Feng , Yueyi Zhang , Weidong Cai , Jiankang Deng , Lidong Bing

Vision-language models (VLMs) are often deployed on text-only inputs, although they are trained with images. We find that removing the vision modality causes large drops in accuracy and severe miscalibration, and the model does not behave…

Computation and Language · Computer Science 2026-05-14 Mingyeong Kim , Jungwon Choi , Chaeyun Jang , Juho Lee

Despite the recent achievements made in the multi-modal emotion recognition task, two problems still exist and have not been well investigated: 1) the relationship between different emotion categories are not utilized, which leads to…

Computation and Language · Computer Science 2020-10-08 Wenliang Dai , Zihan Liu , Tiezheng Yu , Pascale Fung

Multi-modal word semantics aims to enhance embeddings with perceptual input, assuming that human meaning representation is grounded in sensory experience. Most research focuses on evaluation involving direct visual input, however, visual…

Computation and Language · Computer Science 2021-10-07 Anita L. Verő , Ann Copestake

Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., word embeddings,…

Computer Vision and Pattern Recognition · Computer Science 2023-05-29 Wenjia Xu , Yongqin Xian , Jiuniu Wang , Bernt Schiele , Zeynep Akata

Vision Language Models (VLMs) are impressive at visual question answering and image captioning. But they underperform on multi-step visual reasoning -- even compared to LLMs on the same tasks presented in text form -- giving rise to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Simon Park , Abhishek Panigrahi , Yun Cheng , Dingli Yu , Anirudh Goyal , Sanjeev Arora