多模态大模型 - arXivDaily 专题

2501.04686 2025-10-07 cs.CL cs.AI cs.LG 84%

Unlocking Multimodal Mathematical Reasoning via Process Reward Model

Ruilin Luo, Zhuofan Zheng, Yifan Wang, Xinzhe Ni, Zicheng Lin, Songtao Jiang, Yiyao Yu, Chufan Shi, Lei Wang, Ruihang Chu, Jin Zeng, Yujiu Yang

机构 * Tsinghua University（清华大学）； ByteDance（字节跳动）； Zhejiang University（浙江大学）； Ping An Technology (Shenzhen) Co., Ltd（平安科技（深圳）有限公司）

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

Comments NeurIPS 2025 Main Track

2507.16296 2025-10-07 cs.AI 83%

Cross-Modal Distillation For Widely Differing Modalities

Cairong Zhao, Yufeng Jin, Zifan Song, Haonan Chen, Duoqian Miao, Guosheng Hu

机构 * Department of Computer Science & Technology, Tongji University（计算机科学与技术系，同济大学）； Alibaba Group（阿里巴巴集团）； Oosto

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

Comments 14 pages, 9 figures

2510.04136 2025-10-07 eess.AS cs.CV cs.SD 81%

MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition

Umberto Cappellazzo, Minsu Kim, Pingchuan Ma, Honglie Chen, Xubo Liu, Stavros Petridis, Maja Pantic

机构 * Imperial College London（伦敦帝国学院）； Meta AI ； NatWest AI Research（NatWest人工智能研究）

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

Comments NeurIPS 2025

2307.07748 2025-10-07 eess.AS 79%

Leveraging Self-Supervised Audio-Visual Pretrained Models to Improve Vocoded Speech Intelligibility in Cochlear Implant Simulation

Richard Lee Lai, Jen-Cheng Hou, I-Chun Chern, Kuo-Hsuan Hung, Yi-Ting Chen, Mandar Gogate, Tughrul Arslan, Amir Hussain, Yu Tsao

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

2510.04738 2025-10-07 cs.SD cs.AI cs.CL cs.LG eess.AS 67%

Speak, Edit, Repeat: High-Fidelity Voice Editing and Zero-Shot TTS with Cross-Attentive Mamba

Baher Mohammad, Magauiya Zhussip, Stamatios Lefkimmiatis

机构 * MTS AI（MTS人工智能公司）； ITMO University（ITMO大学）

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

2510.03639 2025-10-07 cs.CL cs.AI 62%

Towards Unsupervised Speech Recognition at the Syllable-Level

Liming Wang, Junrui Ni, Kai-Wei Chang, Saurabhchand Bhati, David Harwath, Mark Hasegawa-Johnson, James R. Glass

机构 * Massachusetts Institute of Technology（麻省理工学院）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； University of Texas at Austin（德克萨斯大学奥斯汀分校）

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

2510.04750 2025-10-07 cs.CL cs.SE 57%

A Low-Resource Speech-Driven NLP Pipeline for Sinhala Dyslexia Assistance

Peshala Perera, Deshan Sumanathilaka

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

Comments 11 pages, 4 figures, 3 tables

2510.03336 2025-10-07 cs.SD cs.AI cs.LG 57%

Linguistic and Audio Embedding-Based Machine Learning for Alzheimer's Dementia and Mild Cognitive Impairment Detection: Insights from the PROCESS Challenge

Adharsha Sam Edwin Sam Devahi, Sohail Singh Sangha, Prachee Priyadarshinee, Jithin Thilakan, Ivan Fu Xing Tan, Christopher Johann Clarke, Sou Ka Lon, Balamurali B T, Yow Wei Quin, Chen Jer-Ming

机构 * Singapore University of Technology and Design（新加坡科技设计大学）； Hochschule für Musik Detmold（音乐学院Detmold）

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

1. 音频语音多模态 8 篇

Unlocking Multimodal Mathematical Reasoning via Process Reward Model

Cross-Modal Distillation For Widely Differing Modalities

MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition

Leveraging Self-Supervised Audio-Visual Pretrained Models to Improve Vocoded Speech Intelligibility in Cochlear Implant Simulation

Speak, Edit, Repeat: High-Fidelity Voice Editing and Zero-Shot TTS with Cross-Attentive Mamba

Towards Unsupervised Speech Recognition at the Syllable-Level

A Low-Resource Speech-Driven NLP Pipeline for Sinhala Dyslexia Assistance

Linguistic and Audio Embedding-Based Machine Learning for Alzheimer's Dementia and Mild Cognitive Impairment Detection: Insights from the PROCESS Challenge