Tao Ye (陶也)
Tao Ye (陶也)
M.S. student in Artificial Intelligence at Nanjing University Speech Group (2026-2029), advised by Prof. Shuai Wang.
B.Eng. in Artificial Intelligence, SJTU (2022-2026).

I am Tao Ye (陶也), an M.S. student at the Nanjing University Speech Group (2026–2029), advised by Prof. Shuai Wang. I received my B.Eng. in Artificial Intelligence from Shanghai Jiao Tong University (SJTU), where I was in the AI Talents Pilot Class and the Zhiyuan Honors Program.

Research Interests

  • General audio generation
  • Audio-visual generation
  • Dialogue systems
  • Spoken language models

Education

  1. 2026 – 2029
    Nanjing University (NJU)
    M.S. in Artificial Intelligence

    Speech Group, advised by Prof. Shuai Wang.

  2. 2022 – 2026
    Shanghai Jiao Tong University (SJTU)
    B.Eng. in Artificial Intelligence

    AI Talents Pilot Class, Zhiyuan Honors Program, X-LANCE Lab.

Experience

  1. Dec 2025 – Present
    Video Rebirth
    Research Intern

    Working on unified audio-visual generation and VTA / V2ST tasks.

  2. Jun 2025 – Dec 2025
    Shanghai AI Laboratory (Speech Group)
    Research Intern

    Supervised by Prof. Chao Zhang.

Selected Publications

Full list on Publications. Ye Tao is highlighted.

  • First author arXiv 2026
    Foley-Omni: A Unified Multimodal Generation Model from Task-Level Audio Synthesis to Complete Video Soundtrack Generation
    Ye Tao, Lupeng Liu, Xuenan Xu, Jiasun Feng, Jiarui Wang, Ying Qin, Shuiyang Mao, Wei Liu, Shuai Wang

    Unified multimodal generation of speech, sound effects, and music for complete video soundtracks.

    arXiv Project Code
  • First author ICME 2026
    MMEdit: A Unified Framework for Multi-Type Audio Editing via Audio Language Model
    Ye Tao, Wen Wu, Chao Zhang, Shuai Wang, Mengyue Wu, Xuenan Xu

    Unified editing across addition, replacement, removal, reordering, and attribute modification.

    arXiv Project
  • arXiv 2025
    UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities
    Xuenan Xu, Jiahao Mei, Zihao Zheng, Ye Tao, Zeyu Xie, Yaoyun Zhang, Haohe Liu, Yuning Wu, Ming Yan, Wen Wu, Chao Zhang, Mengyue Wu

    Unified flow matching for omni-modal audio generation across aligned and non-aligned tasks.

    arXiv Project

Contact

Honors

  • Zhiyuan Honors Program, Shanghai Jiao Tong University
  • AI Talents Pilot Class, Shanghai Jiao Tong University