Shanghai, China

Xiquan Li

Advanced
@xiquan-li

Master student @ SJTU & Télécom Paris. Research Intern @ByteDance-Seed | Prev: @Tencent-Hunyuan

xiquan-li.github.io

MeanAudio. [ACL 2026 Main] MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows

145

Awesome-Audio-Generation. Curated list for papers, codes and resources related to Text-to-Audio (TTA) Generation

75

Resonate. [INTERSPEECH 2026] Pre-training, SFT, DPO and GRPO for Text-to-Audio Generation

48

TinyMU. [ICASSP 2026] TinyMU: A Compact Audio Language Model for Music Understanding

37

FineLAP. [ACL 2026 Main] FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pre-training

36

INF224-Project. Final project of course INF224 at Telecom Paris

2

xiquan-li.github.io. HTML

2
7
Apply