多模态大模型

SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval

Yuqi Xiao, Yingying Zhu

机构 * Yuqi Xiao, Yingying Zhu 纠错

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.CV

DINOReg: Strong Point Cloud Registration with Vision Foundation Model

Congjia Chen, Yufu Qu

机构 * School of Instrumentation and Optoelectronic Engineering（仪器与光电工程学院） 纠错

专题命中 跨模态检索 ：multi-modal(abstract)；分类 cs.CV

TATTOO: Training-free AesTheTic-aware Outfit recOmmendation

Yuntian Wu, Xiaonan Hu, Ziqi Zhou, Hao Lu

机构 * Huazhong University of Science and Technology（华中科技大学） 纠错

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.CV

Comments 4 figures, 4 tables

HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores

Guohang Yan, Yue Zhang, Pinlong Cai, Ding Wang, Song Mao, Hongwei Zhang, Yaoze Zhang, Hairong Zhang, Xinyu Cai, Botian Shi

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

专题命中 跨模态检索 ：cross-modal(abstract)；分类 cs.CL

Comments 15 pages, 4 figures

Semantic Edge-Cloud Communication for Real-Time Urban Traffic Surveillance with ViT and LLMs over Mobile Networks

Murat Arda Onsu, Poonam Lohan, Burak Kantarci, Aisha Syed, Matthew Andrews, Sean Kennedy

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.AI

Comments 17 pages, 12 figures

Proxy-Embedding as an Adversarial Teacher: An Embedding-Guided Bidirectional Attack for Referring Expression Segmentation Models

Xingbai Chen, Tingchao Fu, Renyang Liu, Wei Zhou, Chao Yi

机构 * National Pilot School of Software, Yunnan University（云南大学软件试点学校） ； School of Information Science and Engineering, Yunnan University（云南大学信息科学与工程学院） ； Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所） 纠错

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.CV

Comments 20pages, 5figures

EPIC: Generative AI Platform for Accelerating HPC Operational Data Analytics

Ahmad Maroof Karimi, Woong Shin, Jesse Hines, Tirthankar Ghosal, Naw Safrin Sattar, Feiyi Wang

机构 * National Center for Computational Sciences（国家计算科学中心） ； Oak Ridge National Laboratory（橡树岭国家实验室） 纠错

专题命中 跨模态检索 ：multi-modal(abstract)；分类 cs.AI

Reply with Sticker: New Dataset and Model for Sticker Retrieval

Bin Liang, Bingbing Wang, Zhixin Bai, Qiwei Lang, Mingwei Sun, Kaiheng Hou, Lanjun Zhou, Ruifeng Xu, Kam-Fai Wong

专题命中 跨模态检索 ：cross-modal(abstract)；分类 cs.MM

Journal ref Liang B, Wang B, Bai Z, et al. Reply with Sticker: New Dataset and Model for Sticker Retrieval[J]. IEEE Transactions on Audio, Speech and Language Processing, 2025

More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era

Yingtai Li, Haoran Lai, Xiaoqian Zhou, Shuai Ming, Wenxin Ma, Wei Wei, Shaohua Kevin Zhou

机构 * School of Biomedical Engineering, Division of Life Sciences ； Medicine, University of Science ； Technology of China (USTC), Hefei Anhui, 230026, China Center for Medical Imaging, Robotics, Analytic Computing \& Learning (MIRACLE), Suzhou Institute for Advance Research, USTC, Suzhou Jiangsu, 215123, China The First Affiliated Hospital of USTC, Division of Life Sciences ； Medicine, USTC, Hefei Anhui, 230001, China Jiangsu Provincial Key Laboratory of Multimodal Digital Twin Technology, Suzhou Jiangsu, 215123, China State Key Laboratory of Precision 纠错

专题命中 跨模态检索 ：cross-modal(abstract)；分类 cs.CV

Comments MICCAI 2025

Tiny-BioMoE: a Lightweight Embedding Model for Biosignal Analysis

Stefanos Gkikas, Ioannis Kyprakis, Manolis Tsiknakis

机构 * Foundation for Research \& Technology-Hellas Heraklion Greece ； Foundation for Research \& Technology-Hellas ； Hellenic Mediterranean University Heraklion Greece ； Hellenic Mediterranean University 纠错

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.AI

A Survey on Retrieval And Structuring Augmented Generation with Large Language Models

Pengcheng Jiang, Siru Ouyang, Yizhu Jiao, Ming Zhong, Runchu Tian, Jiawei Han

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.CL

Comments KDD'25 survey track

Listening for "You": Enhancing Speech Image Retrieval via Target Speaker Extraction

Wenhao Yang, Jianguo Wei, Wenhuan Lu, Xinyue Song, Xianghu Yue

专题命中 跨模态检索 ：multimodal(abstract)；分类 eess.AS

Comments 5 pages, 2 figures

Back To The Drawing Board: Rethinking Scene-Level Sketch-Based Image Retrieval

Emil Demić, Luka Čehovin Zajc

机构 * Faculty of Computer and Information Science University of Ljubljana（计算机与信息科学系卢布尔雅那大学） 纠错

专题命中 跨模态检索 ：cross-modal(abstract)；分类 cs.CV

Comments Accepted to BMVC2025

Preserving Vector Space Properties in Dimensionality Reduction: A Relationship Preserving Loss Framework

Eddi Weinwurm, Alexander Kovalenko

机构 * Department of Applied Mathematics, Faculty of Information Technology, Czech Technical University in Prague（应用数学系，信息科技学院，布拉格捷克技术大学） 纠错

专题命中 跨模态检索 ：cross-modal(abstract)；分类 cs.AI

Uncertainty-Aware Prototype Semantic Decoupling for Text-Based Person Search in Full Images

Zengli Luo, Canlong Zhang, Zhixin Li, Zhiwen Wang, Chunrong Wei

专题命中 跨模态检索 ：cross-modal(abstract)；分类 cs.CV

Comments 9 pages, 5 figures. Accepted by the 18th International Conference on Knowledge Science, Engineering and Management (KSEM 2025)

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization

Ruoxi Cheng, Yizhong Ding, Shuirong Cao, Ranjie Duan, Xiaoshuang Jia, Shaowei Yuan, Simeng Qin, Zhiqiang Wang, Xiaojun Jia

机构 * Alibaba Group（阿里巴巴集团） ； Beijing Electronic Science and Technology Institute（北京电子科技研究所） ； Nanjing University（南京大学） ； Renmin University of China（中国人民大学） ； Northeastern University（东北大学） ； BraneMatrix AI ； Nanyang Technological University（南洋理工大学） 纠错

专题命中 跨模态检索 ：cross-modal(abstract)；分类 cs.AI

Comments Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization

OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation

Junyuan Zhang, Qintong Zhang, Bin Wang, Linke Ouyang, Zichen Wen, Ying Li, Ka-Ho Chow, Conghui He, Wentao Zhang

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； Peking University（北京大学） ； The University of HongKong（香港大学） ； Shanghai Jiaotong University（上海交通大学） ； Beihang University（北京航空航天大学） 纠错

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.CV

Comments Accepted by ICCV 2025

Reference-Aligned Retrieval-Augmented Question Answering over Heterogeneous Proprietary Documents

Nayoung Choi, Grace Byun, Andrew Chung, Ellie S. Paek, Shinsun Lee, Jinho D. Choi

机构 * Department of Computer Science Emory University Atlanta Georgia USA（计算机科学系 埃默里大学 阿拉巴马 州 美国） ； Emory University（埃默里大学） 纠错

专题命中 跨模态检索 ：multi-modal(abstract)；分类 cs.AI

Comments Accepted to CIKM 2025 Applied Research Track

Reasoning LLMs in the Medical Domain: A Literature Survey

Armin Berger, Sarthak Khanna, David Berghaus, Rafet Sifa

机构 * Fraunhofer IAIS - Department of Media Engineering（弗劳恩霍夫研究所媒体工程部门） ； University of Bonn - Department of Computer Science（波恩大学计算机科学系） ； West-AI - Federal Ministry of Education and Research（西德人工智能 - 教育与研究部） 纠错

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.AI

Consciousness as a Functor

Sridhar Mahadevan

机构 * Adobe Research and University of Massachusetts, Amherst（Adobe研究院和马萨诸塞大学） 纠错

专题命中 跨模态检索 ：multi-modal(abstract)；分类 cs.AI

Comments 31 pages

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

Jian Chen, Ming Li, Jihyung Kil, Chenguang Wang, Tong Yu, Ryan Rossi, Tianyi Zhou, Changyou Chen, Ruiyi Zhang

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.CV

Comments Under Review

Demo: Soccer Information Retrieval via Natural Queries using SoccerRAG

Aleksander Theo Strand, Sushant Gautam, Cise Midoglu, Pål Halvorsen

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.MM

Comments accepted to CBMI 2024 as a demonstration; https://github.com/simula/soccer-rag. arXiv admin note: text overlap with arXiv:2406.01273

LGE-Guided Cross-Modality Contrastive Learning for Gadolinium-Free Cardiomyopathy Screening in Cine CMR

Siqing Yuan, Yulin Wang, Zirui Cao, Yueyan Wang, Zehao Weng, Hui Wang, Lei Xu, Zixian Chen, Lei Chen, Zhong Xue, Dinggang Shen

机构 * School of Biomedical Engineering（生物医学工程学院） ； State Key Laboratory of Advanced Medical Materials and Devices（先进医疗材料与设备国家重点实验室） ； ShanghaiTech University（上海科技大学） ； United Imaging Intelligence（联合影像智能） ； Shanghai Clinical Research and Trial Center（上海临床研究与试验中心） ； Capital Medical University（首都医科大学） ； The First Hospital of Lanzhou University（兰州大学第一医院） 纠错

专题命中 跨模态检索 ：cross-modal(abstract)；分类 cs.CV

Comments Accepted to MLMI 2025 (MICCAI workshop); camera-ready version

Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrieval

Jonghyun Song, Youngjune Lee, Gyu-Hwung Cho, Ilhyeon Song, Saehun Kim, Yohan Jo

机构 * Graduate School of Data Science, Seoul National University（首尔国立大学数据科学研究生院） ； NAVER Corporation（NAVER公司） 纠错

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.CL

Comments accepted to CIKM 2025 short research paper track

Contributions to Label-Efficient Learning in Computer Vision and Remote Sensing

Minh-Tan Pham

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.CV

Comments Habilitation à Diriger des Recherches (HDR) manuscript

VELVET-Med: Vision and Efficient Language Pre-training for Volumetric Imaging Tasks in Medicine

Ziyang Zhang, Yang Yu, Xulei Yang, Si Yong Yeo

机构 * MedVisAI Lab Department of ECE Northwestern University（MedVisAI实验室 电子工程系 西北大学） ； Institute for Infocomm Research (I 2 R) A*STAR, Singapore（信息与通信研究所（I 2 R）A*STAR，新加坡） ； MedVisAI Lab Lee Kong Chian School of Medicine, Nanyang Technological University（MedVisAI实验室 李科田医学院，南洋理工大学） 纠错

专题命中 跨模态检索 ：cross-modal(abstract)；分类 cs.CV

The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers

Xingyu Deng, Xi Wang, Mark Stevenson

机构 * University of Sheffield（谢菲尔德大学） 纠错

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.CL

Comments Accepted for ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR'25)

FinSage: A Multi-aspect RAG System for Financial Filings Question Answering

Xinyu Wang, Jijun Chi, Zhenghan Tai, Tung Sum Thomas Kwok, Muzhi Li, Zhuhong Li, Hailin He, Yuchen Hua, Peng Lu, Suyuchen Wang, Yihong Wu, Jerry Huang, Jingrui Tian, Fengran Mo, Yufei Cui, Ling Zhou

机构 * 1SimpleWay.AI 2McGill University 3University of Toronto 4University of California, Los Angeles 5The Chinese University of Hong Kong 6Duke University 7Universit\'e de Montr\'eal 8Mila - Quebec AI Institute 9Noah's Ark Lab 10CG Matrix Technology Limited ； 1SimpleWay.AI 2McGill University 3University of Toronto 4University of California, Los Angeles ； 5The Chinese University of Hong Kong 6Duke University 7Universit\'e de Montr\'eal 8Mila - Quebec AI Institute ； 9Noah's Ark Lab 10CG Matrix Technology Limited 纠错

专题命中 跨模态检索 ：multi-modal(abstract)；分类 cs.AI

Comments Accepted at the 34th ACM International Conference on Information and Knowledge Management (CIKM2025)

MIDAS: Modeling Ground-Truth Distributions with Dark Knowledge for Domain Generalized Stereo Matching

Peng Xu, Zhiyu Xiang, Jingyun Fu, Tianyu Pu, Hanzhi Zhong, Eryun Liu

机构 * Zhejiang University, China（浙江大学） 纠错

专题命中 跨模态检索 ：multi-modal(abstract)；分类 cs.CV

EMPATHIA: Multi-Faceted Human-AI Collaboration for Refugee Integration

Mohamed Rayan Barhdadi, Mehmet Tuncel, Erchin Serpedin, Hasan Kurban

机构 * Texas A&M University（德克萨斯A&M大学） ； Istanbul Technical University（伊斯坦布尔技术大学） ； Hamad Bin Khalifa University（哈利法大学） 纠错

专题命中 跨模态检索 ：multimodal(abstract)；分类 cs.AI

Comments 19 pages, 3 figures (plus 6 figures in supplementary), 2 tables, 1 algorithm. Submitted to NeurIPS 2025 Creative AI Track: Humanity