English
Related papers

Related papers: Topology-Aware Representation Alignment for Semi-S…

200 papers

We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitations with extended narratives through a multi-layered…

Computation and Language · Computer Science 2018-08-07 Patrick Huber , Jan Niehues , Alex Waibel

Ontology Alignment is an important research problem applied to various fields such as data integration, data transfer, data preparation, etc. State-of-the-art (SOTA) Ontology Alignment systems typically use naive domain-dependent approaches…

Computation and Language · Computer Science 2021-12-20 Vivek Iyer , Arvind Agarwal , Harshit Kumar

Representation learning on graphs is a fundamental problem that can be crucial in various tasks. Graph neural networks, the dominant approach for graph representation learning, are limited in their representation power. Therefore, it can be…

Machine Learning · Computer Science 2025-01-17 Zuoyu Yan , Qi Zhao , Ze Ye , Tengfei Ma , Liangcai Gao , Zhi Tang , Yusu Wang , Chao Chen

To address a fundamental limitation in cognitive systems, namely the absence of a time-updatable mediating thought space between semantics and continuous control, this work constructs and trains a vision-language-action model termed Sigma,…

Machine Learning · Computer Science 2026-01-23 Libo Wang

Surface roughness plays an important role in analyzing engineering surfaces. It quantifies the surface topography and can be used to determine whether the resulting surface finish is acceptable or not. Nevertheless, while several existing…

Signal Processing · Electrical Eng. & Systems 2021-10-20 Melih C. Yesilli , Firas A. Khasawneh

Recently, Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs). However, existing approaches often…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Wayner Barrios , Andrés Villa , Juan León Alcázar , SouYoung Jin , Bernard Ghanem

An elusive goal in navigation research is to build an intelligent agent that can understand multimodal instructions including natural language and image, and perform useful navigation. To achieve this, we study a widely useful category of…

Homography estimation is the task of determining the transformation from an image pair. Our approach focuses on employing detector-free feature matching methods to address this issue. Previous work has underscored the importance of…

Information Retrieval · Computer Science 2024-10-15 Yuhan Liu , Qianxin Huang , Siqi Hui , Jingwen Fu , Sanping Zhou , Kangyi Wu , Pengna Li , Jinjun Wang

Persistent homology is a tool from Topological Data Analysis (TDA) used to summarize the topology underlying data. It can be conveniently represented through persistence diagrams. Observing a noisy signal, common strategies to infer its…

Statistics Theory · Mathematics 2024-08-28 Hugo Henneuse

The expansion of instruction-tuning data has enabled foundation language models to exhibit improved instruction adherence and superior performance across diverse downstream tasks. Semantically-rich 3D human motion is being progressively…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Lei Hu , Yongjing Ye , Shihong Xia

Brain networks/graphs derived from resting-state functional MRI (fMRI) help study underlying pathophysiology of neurocognitive disorders by measuring neuronal activities in the brain. Some studies utilize learning-based methods for brain…

Image and Video Processing · Electrical Eng. & Systems 2024-11-05 Qianqian Wang , Wei Wang , Yuqi Fang , Hong-Jun Li , Andrea Bozoki , Mingxia Liu

Multimodal pathology-genomic analysis has become increasingly prominent in cancer survival prediction. However, existing studies mainly utilize multi-instance learning to aggregate patch-level features, neglecting the information loss of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Mingcheng Qu , Guang Yang , Donglin Di , Tonghua Su , Yue Gao , Yang Song , Lei Fan

Most existing methods in vision-language retrieval match two modalities by either comparing their global feature vectors which misses sufficient information and lacks interpretability, detecting objects in images or videos and aligning the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Xiaohan Zou , Changqiao Wu , Lele Cheng , Zhongyuan Wang

Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications. The prevailing approach to aligning vision and language models involves freezing both the vision encoder and the language model while…

Machine Learning · Computer Science 2025-07-01 Yuanze Hu , Zhaoxin Fan , Xinyu Wang , Gen Li , Ye Qiu , Zhichao Yang , Wenjun Wu , Kejian Wu , Yifan Sun , Xiaotie Deng , Jin Dong

Vision-Language Pre-training (VLP) has achieved impressive performance on various cross-modal downstream tasks. However, most existing methods can only learn from aligned image-caption data and rely heavily on expensive regional features,…

Computer Vision and Pattern Recognition · Computer Science 2022-03-18 Wei Li , Can Gao , Guocheng Niu , Xinyan Xiao , Hao Liu , Jiachen Liu , Hua Wu , Haifeng Wang

Vision-language models (VLMs) struggle in open-world applications, where out-of-distribution (OOD) concepts often trigger cross-modal alignment collapse and severely degrade zero-shot performance. We identify the root cause as modal…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Jensen Zhang , Ningyuan Liu , Keze Wang

Multimodal recommendation enhances accuracy by leveraging visual and textual signals, and its success largely depends on learning high-quality cross-modal representations. Recent advances in Large Vision-Language Models (LVLMs) offer…

Information Retrieval · Computer Science 2026-04-28 Zhongtao Rao , Peilin Zhou , Dading Chong , Zhiwei Chen , Shoujin Wang , Nan Tang

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

Although text recognition has significantly evolved over the years, state-of-the-art (SOTA) models still struggle in the wild scenarios due to complex backgrounds, varying fonts, uncontrolled illuminations, distortions and other artefacts.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-28 Ayan Kumar Bhunia , Aneeshan Sain , Amandeep Kumar , Shuvozit Ghose , Pinaki Nath Chowdhury , Yi-Zhe Song

Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered…

Quantitative Methods · Quantitative Biology 2017-11-01 Zixuan Cang , Guo-Wei Wei