多模态大模型

Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization

Jiulong Wu, Zhengliang Shi, Shuaiqiang Wang, Jizhou Huang, Dawei Yin, Lingyong Yan, Min Cao, Min Zhang

机构 * Soochow University（苏州大学） ； Baidu Inc.（百度公司） ； Shandong University（山东大学） 纠错

专题命中 图文多模态 ：multimodal(title,abstract)；image-text(abstract)；分类 cs.CV、cs.CL、cs.AI

Comments This paper is accepted by EMNLP2025

Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification

Tuo Xiang, Xuemiao Xu, Bangzhen Liu, Jinyi Li, Yong Li, Shengfeng He

机构 * South China University of Technology（南方科技大学） ； State Key Laboratory of Subtropical Building Science（亚热带建筑科学国家重点实验室） ； Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information（广东省计算智能与网络信息重点实验室） ； Ministry of Education Key Laboratory of Big Data and Intelligent Robot（教育部大数据与智能机器人重点实验室） ； Singapore Management University（新加坡国立大学） 纠错

专题命中 图文多模态 ：cross-modal(title,abstract)；分类 cs.CV

Comments ICCV2025

MedCutMix: A Data-Centric Approach to Improve Radiology Vision-Language Pre-training with Disease Awareness

Sinuo Wang, Yutong Xie, Yuyuan Liu, Qi Wu

机构 * The University of Adelaide（阿德莱德大学） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； University of Oxford（牛津大学） 纠错

专题命中 图文多模态 ：multi-modal(abstract)；image-text(abstract)；分类 cs.CV

Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization

Ji Soo Lee, Byungoh Ko, Jaewon Cho, Howoong Lee, Jaewoon Byun, Hyunwoo J. Kim

机构 * Korea University（韩国大学） ； Hanwha Vision（翰威英航） ； KAIST（韩国科学技术院） 纠错

专题命中 图文多模态 ：multi-modal(abstract)；MLLM(abstract)；分类 cs.CV

Comments EMNLP 2025 Findings

Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding

Haoyuan Li, Rui Liu, Hehe Fan, Yi Yang

机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） 纠错

专题命中 图文多模态 ：multimodal(abstract)；分类 cs.CV、cs.AI

Comments 19 pages, 12 figures, 6 tables

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts

Xuyang Wu, Yuan Wang, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang

机构 * Santa Clara University（圣克拉拉大学） ； DOCOMO Innovations, Inc.（DOCOMO创新公司） ； Rochester Institute of Technology（罗切斯特理工学院） 纠错

专题命中 图文多模态 ：multi-modal(abstract)；分类 cs.CV、cs.CL

Comments EMNLP Findings

Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP

Jiawei Kong, Hao Fang, Sihang Guo, Chenxi Qing, Kuofeng Gao, Bin Chen, Shu-Tao Xia, Ke Xu

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院，清华大学） ； School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院） ； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） 纠错

专题命中 图文多模态 ：multimodal(abstract)；分类 cs.CV

ViLReF: An Expert Knowledge Enabled Vision-Language Retinal Foundation Model

Shengzhu Yang, Jiawei Du, Jia Guo, Weihang Zhang, Hanruo Liu, Huiqi Li, Ningli Wang

机构 * Beijing Institute of Technology（北京理工大学） ； Beijing Key Laboratory of Intelligent Diagnosis Technology and Equipment for Optic Nerve-Related Eye Diseases（北京智能诊断技术与设备重点实验室） ； Tsinghua University（清华大学） ； Beijing Tongren Hospital, Capital Medical University（北京同仁医院） ； Henan Academy of Innovations in Medical Science（河南医学创新研究院） 纠错

专题命中 图文多模态 ：image-text(abstract)；分类 cs.CV

DA-Mamba: Dialogue-aware selective state-space model for multimodal engagement estimation

Shenwei Kang, Xin Zhang, Wen Liu, Bin Li, Yujie Liu, Bo Gao

机构 * Communication University of China（中国通信大学） ； Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院） ； School of Information Engineering, Beijing Institute of Graphic Communication（北京印刷学院信息工程学院） 纠错

专题命中 音频语音多模态 ：multimodal(title,abstract)；cross-modal(abstract)；分类 cs.AI

Audio-Guided Dynamic Modality Fusion with Stereo-Aware Attention for Audio-Visual Navigation

Jia Li, Yinfeng Yu, Liejun Wang, Fuchun Sun, Wendong Zheng

机构 * Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center（新疆多模态智能处理与信息安全工程技术创新中心） ； School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院） ； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； School of Electrical Engineering and Automation, Tianjin University of Technology（天津理工大学电气工程与自动化学院） 纠错

专题命中 音频语音多模态 ：audio-visual(title,abstract)；multi-modal(abstract)；分类 cs.AI

Comments Main paper (14 pages). Accepted for publication by ICONIP( International Conference on Neural Information Processing) 2025

The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio

Renhao Wang, Haoran Geng, Tingle Li, Feishi Wang, Gopala Anumanchipalli, Trevor Darrell, Boyi Li, Pieter Abbeel, Jitendra Malik, Alexei A. Efros

机构 * University of California, Berkeley（加州大学伯克利分校） 纠错

专题命中 音频语音多模态 ：multimodal(title,abstract)；分类 cs.CV

Comments Conference on Robot Learning 2025

SwarmChat: An LLM-Based, Context-Aware Multimodal Interaction System for Robotic Swarms

Ettilla Mohiuddin Eumi, Hussein Abbass, Nadine Marcus

机构 * School of Systems & Computing, UNSW Canberra（系统与计算学院，UNSW堪培拉） ； School of Computer Science and Engineering, UNSW Sydney（计算机科学与工程学院，UNSW悉尼） 纠错

专题命中 音频语音多模态 ：multimodal(title,abstract)

Comments This paper has been accepted and presented at the 16th International Conference on Swarm Intelligence (ICSI 2025), held on July 11-15, 2025, in Yokohama, Japan

Qwen3-Omni Technical Report

Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zhang, Xinyu Zhang, Hongkun Hao, Zishan Guo, Baosong Yang, Bin Zhang, Ziyang Ma, Xipin Wei, Shuai Bai, Keqin Chen, Xuejing Liu, Peng Wang, Mingkun Yang, Dayiheng Liu, Xingzhang Ren, Bo Zheng, Rui Men, Fan Zhou, Bowen Yu, Jianxin Yang, Le Yu, Jingren Zhou, Junyang Lin

机构 * Qwen Team（通义实验室） 纠错

专题命中 音频语音多模态 ：multimodal(abstract)；audio-visual(abstract)；分类 cs.CV、cs.CL、cs.AI

Comments https://github.com/QwenLM/Qwen3-Omni

Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models

María Andrea Cruz Blandón, Zakaria Aldeneh, Jie Chi, Maureen de Seyssel

机构 * Tampere University Apple（塔尔库大学苹果） 纠错

专题命中 音频语音多模态 ：audio-visual(title)；分类 cs.CL、eess.AS

Comments 5 pages, 2 figures

PGSTalker: Real-Time Audio-Driven Talking Head Generation via 3D Gaussian Splatting with Pixel-Aware Density Control

Tianheng Zhu, Yinfeng Yu, Liejun Wang, Fuchun Sun, Wendong Zheng

机构 * Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center（新疆多模态智能处理与信息安全工程技术创新研究中心） ； School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院） ； Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系） ； School of Electrical Engineering and Automation, Tianjin University of Technology（天津理工大学电气工程与自动化学院） 纠错

专题命中 音频语音多模态 ：multimodal(abstract)；audio-visual(abstract)；分类 cs.AI

Comments Main paper (15 pages). Accepted for publication by ICONIP( International Conference on Neural Information Processing) 2025

Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models

Zhifei Xie, Mingbao Lin, Zihang Liu, Pengcheng Wu, Shuicheng Yan, Chunyan Miao

机构 * Nanyang Technological University（南洋理工大学） ； National University of Singapore（国立新加坡大学） ； Rakuten 纠错

专题命中 音频语音多模态 ：multimodal(abstract)；分类 cs.CL、cs.AI、cs.MM

Comments Technical report, in process

Whisper-UT: A Unified Translation Framework for Speech and Text

Cihan Xiao, Matthew Wiesner, Debashish Chakraborty, Reno Kriz, Keith Cunningham, Kenton Murray, Kevin Duh, Luis Tavarez-Arce, Paul McNamee, Sanjeev Khudanpur

机构 * Center for Language and Speech Processing, Johns Hopkins University（语言与语音处理中心，约翰霍普金斯大学） ； Human Language Technology Center of Excellence, Johns Hopkins University（人类语言技术卓越中心，约翰霍普金斯大学） ； Georgetown University（乔治城大学） 纠错

专题命中 音频语音多模态 ：multi-modal(abstract)；cross-modal(abstract)；分类 cs.CL

Comments EMNLP 2025 Main Conference

VAInpaint: Zero-Shot Video-Audio inpainting framework with LLMs-driven Module

Kam Man Wu, Zeyue Tian, Liya Ji, Qifeng Chen

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学） 纠错

专题命中 音频语音多模态 ：audio-visual(abstract)；分类 cs.CV、cs.MM、eess.AS

Speech-to-See: End-to-End Speech-Driven Open-Set Object Detection

Wenhuan Lu, Xinyue Song, Wenjun Ke, Zhizhi Yu, Wenhao Yang, Jianguo Wei

机构 * College of Intelligence and Computing, Tianjin University, Tianjin, China（智能与计算学院，天津大学，天津，中国） ； PipeChina Institute of Science and Technology, Tianjin, China（中石油科技研究院，天津，中国） 纠错

专题命中 音频语音多模态 ：cross-modal(abstract)；分类 cs.MM、eess.AS

STAR: Speech-to-Audio Generation via Representation Learning

Zeyu Xie, Xuenan Xu, Yixuan Li, Mengyue Wu, Yuexian Zou

机构 * Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Peking University, Shenzhen（广东超高清沉浸媒体技术重点实验室，北京大学深圳校区） ； X-LANCE Lab, Shanghai Jiao Tong University, Shanghai（X-LANCE实验室，上海交通大学） 纠错

专题命中 音频语音多模态 ：multimodal(abstract)；分类 eess.AS

What's Not on the Plate? Rethinking Food Computing through Indigenous Indian Datasets

Pamir Gogoi, Neha Joshi, Ayushi Pandey, Deepthi Sudharsan, Saransh Kumar Gupta, Lipika Dey, Partha Pratim Das, Kalika Bali, Vivek Seshadri

专题命中 音频语音多模态 ：multimodal(abstract)

Serendipitous Recommendation with Multimodal LLM

Haoting Wang, Jianling Wang, Hao Li, Fangjun Yi, Mengyu Fu, Youwei Zhang, Yifan Liu, Liang Liu, Minmin Chen, Ed H. Chi, Lichan Hong, Haokai Lu

专题命中 视频多模态 ：multimodal(title,abstract)；MLLM(abstract)

Comments Accepted by 2025 Recsys EARL Workshop

RCTDistill: Cross-Modal Knowledge Distillation Framework for Radar-Camera 3D Object Detection with Temporal Fusion

Geonho Bang, Minjae Seong, Jisong Kim, Geunju Baek, Daye Oh, Junhyung Kim, Junho Koh, Jun Won Choi

机构 * Seoul National University（首尔国立大学） ； Hanyang University（翰阳大学） ； Hyundai Motor Company（现代汽车公司） 纠错

专题命中 视频多模态 ：cross-modal(title,abstract)；分类 cs.CV

Comments Accepted at ICCV 2025

Show-o2: Improved Native Unified Multimodal Models

Jinheng Xie, Zhenheng Yang, Mike Zheng Shou

机构 * Show Lab, National University of Singapore（新加坡国立大学Show实验室） ； ByteDance（字节跳动） 纠错

专题命中 视频多模态 ：multimodal(title,abstract)；分类 cs.CV

Comments NeurIPS 2025. (v3: update to include video understanding, OneIG, and more ablation study results)

ClassMind: Scaling Classroom Observation and Instructional Feedback with Multimodal AI

Ao Qu, Yuxi Wen, Jiayi Zhang, Yunge Wen, Yibo Zhao, Alok Prakash, Andrés F. Salazar-Gómez, Paul Pu Liang, Jinhua Zhao

专题命中 视频多模态 ：multimodal(title,abstract)

TACTFL: Temporal Contrastive Training for Multi-modal Federated Learning with Similarity-guided Model Aggregation

Guanxiong Sun, Majid Mirmehdi, Zahraa Abdallah, Raul Santos-Rodriguez, Ian Craddock, Telmo de Menezes e Silva Filho

专题命中 视频多模态 ：multi-modal(title,abstract)

Diffusion-Based Approximate MPC: Fast and Consistent Imitation of Multi-Modal Action Distributions

Pau Marquez Julbe, Julian Nubert, Henrik Hose, Sebastian Trimpe, Katherine J. Kuchenbecker

机构 * Max Planck ETH CLS（马克斯·普朗克-ETH CLS） ； German Research Foundation（德国研究基金会） ； Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所） ； ETH Zürich（苏黎世联邦理工学院） ； Institute for Data Science in Mechanical Engineering (DSME)（机械工程数据科学研究所） ； RWTH Aachen University（亚琛工业大学） 纠错

专题命中 视频多模态 ：multi-modal(title,abstract)

SD-VSum: A Method and Dataset for Script-Driven Video Summarization

Manolis Mylonas, Evlampios Apostolidis, Vasileios Mezaris

机构 * ITI, CERTH（ITI、CERTH） 纠错

专题命中 视频多模态 ：multimodal(abstract)；cross-modal(abstract)；分类 cs.CV、cs.AI、cs.MM

Comments In ACM Multimedia 2025, DOI:10.1145/3746027.3755821

Trainee Action Recognition through Interaction Analysis in CCATT Mixed-Reality Training

Divya Mereddy, Marcos Quinones-Grueiro, Ashwin T S, Eduardo Davalos, Gautam Biswas, Kent Etherton, Tyler Davis, Katelyn Kay, Jill Lear, Benjamin Goldberg

专题命中 视频多模态 ：multimodal(abstract)；分类 cs.CV、cs.AI

Generate the browsing process for short-video recommendation

Chao Feng, Yanze Zhang, Chenghao Zhang

机构 * Kuaishou Technology（快手科技） 纠错

专题命中 视频多模态 ：multimodal(abstract)；分类 cs.AI