多模态大模型 - arXivDaily 专题

2507.16343 2025-10-28 cs.SD cs.AI eess.AS 84%

Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries

Pengfei Cai, Yan Song, Qing Gu, Nan Jiang, Haoyu Song, Ian McLoughlin

机构 * University of Science and Technology of China（科学技术大学）； Singapore Institute of Technology（新加坡理工学院）

专题命中音频语音多模态：multi-modal(title,abstract)；cross-modal(abstract)；分类 cs.AI、eess.AS

Comments Accepted by MM 2025

2506.00358 2025-10-28 cs.SD cs.AI cs.LG eess.AS 84%

$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time

Sarthak Kumar Maharana, Saksham Singh Kushwaha, Baoming Zhang, Adrian Rodriguez, Songtao Wei, Yapeng Tian, Yunhui Guo

机构 * The University of Texas at Dallas（德克萨斯大学达拉斯分校）

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

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Track on Datasets and Benchmarks

2504.19549 2025-10-28 cs.CV 83%

DEEMO: De-identity Multimodal Emotion Recognition and Reasoning

Deng Li, Bohao Xing, Xin Liu, Baiqiang Xia, Bihan Wen, Heikki Kälviäinen

机构 * Lappeenranta-Lahti University of Technology LUT（拉普兰塔-拉赫蒂技术大学）； Nanyang Technological University（南洋理工大学）； Brno University of Technology（布拉格技术大学）

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

Comments Accepted by ACMMM 2025

Journal ref Proceedings of the 33rd ACM International Conference on Multimedia (2025)

2506.17113 2025-10-28 cs.CV cs.AI cs.CL 82%

MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation

Shoubin Yu, Yue Zhang, Ziyang Wang, Jaehong Yoon, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校）； Nanyang Technological University（南洋理工大学）

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

Comments EMNLP 2025 Findings; The first two authors contributed equally; Github link: https://github.com/Yui010206/MEXA

2510.22455 2025-10-28 cs.SD cs.AI eess.AS 81%

Evaluating Multimodal Large Language Models on Core Music Perception Tasks

Brandon James Carone, Iran R. Roman, Pablo Ripollés

机构 * Department of Psychology, Music and Audio Research Laboratory（心理学系、音乐与音频研究实验室）； Department of Electronic Engineering and Computer Science（电子工程与计算机科学系）

专题命中音频语音多模态：multimodal(title,abstract)；分类 cs.AI、eess.AS

Comments Accepted to the NeurIPS 2025 Workshop on AI for Music (AI4Music), 16 pages, 1 figure, 3 tables

2508.04273 2025-10-28 cs.IR cs.CV cs.MM cs.SD eess.AS 67%

Audio Does Matter: Importance-Aware Multi-Granularity Fusion for Video Moment Retrieval

Junan Lin, Daizong Liu, Xianke Chen, Xiaoye Qu, Xun Yang, Jixiang Zhu, Sanyuan Zhang, Jianfeng Dong

机构 * Zhejiang University（浙江大学）； Peking University（北京大学）； Zhejiang Gongshang University（浙江工商大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； University of Science and Technology of China（中国科学技术大学）

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

Comments Accepted to ACM MM 2025

2506.21864 2025-10-28 cs.CL cs.AI 62%

DeepOmni: Towards Seamless and Smart Speech Interaction with Adaptive Modality-Specific MoE

Hang Shao, Heting Gao, Yunhang Shen, Jiawei Chen, Zuwei Long, Dong Yang, Ke Li, Xing Sun

机构 * Tencent（腾讯）； Fudan University（复旦大学）

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

Comments Under Review

1. 音频语音多模态 7 篇