About me

Short Bio

I am Tao Ye, currently an undergraduate student in Artificial Intelligence at Shanghai Jiao Tong University (SJTU), in the AI Talents Pilot Class and Zhiyuan Honors Program.

I will join the Nanjing University Speech Group as an M.S. student (2026-2029), advised by Prof. Shuai Wang.

My research focuses on general audio generation and audio-visual generation, especially controllable generation and editing in multimodal settings.

---

Basic Information

• Name: Tao Ye
• Email: ty0402@gmail.com
• GitHub: https://github.com/ty0402
• Google Scholar: TODO

---

Education

• Shanghai Jiao Tong University (SJTU), Shanghai, China
  B.Eng. in Artificial Intelligence, 2022-2026
  AI Talents Pilot Class, Zhiyuan Honors Program, X-LANCE Lab

• Nanjing University (NJU), Nanjing, China
  M.S. Student (Incoming), Speech Group, 2026-2029
  Advisor: Prof. Shuai Wang

---

Research Interests

• General audio generation
• Dialogue systems
• Spoken language models

---

Experience

• Research Intern, Shanghai AI Laboratory (Speech Group), Jun 2025 - Dec 2026
  Supervised by Prof. Chao Zhang.

• Research Intern, Video Rebirth, Dec 2026 - Present
  Working on unified audio-visual generation and VTA tasks.

---

Selected Publications

• MMEdit: A Unified Framework for Multi-Type Audio Editing via Audio Language Model
  Ye Tao, Xuenan Xu, Wen Wu, Shuai Wang, Mengyue Wu, Chao Zhang.
  arXiv preprint, 2025. arXiv | Project

• 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.
  arXiv preprint, 2025. arXiv | Project

---

Honors

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