About Me

I am a senior undergraduate student majoring in Artificial Intelligence (Yao Class) at the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, where I am also minoring in Mathematics.

My research interests lie in high-quality and efficient Generative Models across various modalities, including image, video, audio, speech, and language.

My research experience encompasses an independent project in speech and audio synthesis. I have been fortunate to collaborate with Prof. Chuang Gan on speech language models and video-to-audio generation, with Prof. Zhuang Liu on image generative models.

Publications & Preprints

1. WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching
Tianze Luo, Xingchen Miao, Wenbo Duan
NAACL 2025, Main Conference
[PDF] [Code]

2. BSLM: A Bi-Level Speech-Language Model for the Joint Modeling of Discrete and Continuous Tokens
Tianze Luo, Zixin Wang, Kaizhi Qian, Yang Zhang, Chuang Gan
AAAI Workshop on Audio-Centric AI, 2026
[PDF] [Demo]

3. SoFlow: Solution Flow Models for One-Step Generative Modeling
Tianze Luo, Haotian Yuan, Zhuang Liu
International Conference on Learning Representations (ICLR), 2026
[PDF] [Code]

4. [Under Review] SoundVCM: Efficient Video-to-Audio Generation with Velocity Consistency Models
Tianze Luo, Xingchen Miao, Yang Zhang, Lie Lu, Chuang Gan
Under Review at CVPR 2026
[PDF] [Code]