About Me

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

My research interests are centered on advancing the frontiers of generative models across a broad range of data modalities, including, but not limited to, image, video, audio, speech, and language.

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

5. [Under Review] i1: Simple and Open Recipes for Pre-training Strong Text-to-Image Models
Boya Zeng, Tianze Luo, Shu Pu, Jucheng Shen, Taiming Lu, Gabriel Herbert Sarch, Zhuang Liu

6. [Under Review] What kills v-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching
Tianze Luo, Haofeng Huang, Yuan Yao