Yuxuan Jiang

江宇轩 PhD Student Tsinghua University jiangyux25@mails.tsinghua.edu.cn

I am Yuxuan Jiang (江宇轩), a PhD student at Tsinghua University. My research interests include multimodal learning, diffusion models, and audio generation.
I study unified representations for speech, environmental sounds, and music that capture acoustic details, semantic content, and temporal structure. I also explore cross-modal and interaction-driven models that predict how sound evolves, enabling continuous and controllable audio generation grounded in physical and structural priors.

I welcome conversations and collaborations on these and related topics, from informal exchanges to in-depth discussions. Please feel free to reach out by email.

News

[2026.07] 🎉 One paper: CineDub: Scaling End-to-End Video Dubbing to Multi-Speaker Dialogues with Coherent Sound Effects accepted by ACM MM 2026.
[2026.07] 🚀 Our real-time interactive video generation model is released on Vidu S1! I contributed to the speech-driven module and real-time voice interaction. The Technical Report is publicly available.
[2026.06] 🎉 One paper: SR-Edit: Region-Aware Image Editing via Self-Refinement accepted by ECCV 2026.
[2026.06] 🎉 One paper: FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing accepted by Interspeech 2026.
[2026.04] 🎉 One paper: ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling accepted by ACL 2026 Main (Oral, top 15%).
[2026.01] 🚀 Our joint video-audio generation model is released on Vidu Q3 ! I developed the high-fidelity 48 kHz stereo audio VAE that powers its audio generation.
[2026.01] 🎉 One paper: Omni2Sound: Towards Unified Video-Text-to-Audio Generation accepted by CVPR 2026 (Highlight, top 15%).
[2025.07] 🎉 One paper: FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation accepted by ACM MM 2025 (Oral).
[2025.03] 🚀 Our text-to-audio model is released on Vidu Q1 ! I developed the text-to-audio and timing-controlled systems that power its audio generation capabilities.

Selected Publications [Google Scholar]

CineDub: Scaling End-to-End Video Dubbing to Multi-Speaker Dialogues with Coherent Sound Effects

Yusheng Dai, Kangdi Wang, Baolong Gao, Yuxuan Jiang, Weiqiang Wang, Qiuhong Ke, Jianfei Cai^†

ACM International Conference on Multimedia (ACM MM), 2026.

arXiv Project Page

Vidu S1: A Real-Time Interactive Video Generation Model

Jintao Zhang, Kai Jiang, Jintao Chen, Xu Wang, Yang Luo, Yuji Wang, Dechuang Chen, Jungang Li, Chengyang Ye, Marco Chen, Hongzhou Zhu, Min Zhao, Yuxuan Jiang, Zhengkun Huang, Chendong Xiang, Kaiwen Zheng, Haoxu Wang, Xiaohang Wang, Qi Jia, Xin Chen, Yimin Chen, Youhe Jiang, Fangcheng Fu, Zhijie Deng^†, Fan Bao^†, Jianfei Chen^†, Jun Zhu^†

Technical Report, 2026.

arXiv Project Page

SR-Edit: Region-Aware Image Editing via Self-Refinement

Andong Wang, Zehua Chen^†, Yuxuan Jiang, Jun Zhu^†

European Conference on Computer Vision (ECCV), 2026.

arXiv

FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing

Yuxuan Jiang, Mingyang Han, Yusheng Dai, Andong Wang, Tianhong Zhou, Jiaxin Ye, Dongxiao Wang, Haoxiang Shi, Boyu Li, Jun Song, Cheng Yu, Bo Zheng, Weibei Dou, Zehua Chen^†, Jun Zhu^†

Annual Conference of the International Speech Communication Association (INTERSPEECH), 2026.

arXiv Project Page

ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling

Yuxuan Jiang, Zehua Chen, Zeqian Ju, Yusheng Dai, Weibei Dou, Jun Zhu^†

Annual Meeting of the Association for Computational Linguistics (ACL), 2026.

arXiv Project Page Oral

Omni2Sound: Towards Unified Video-Text-to-Audio Generation

Yusheng Dai, Zehua Chen, Yuxuan Jiang, Hongke Qiu, Jian Fei, Jun Zhu^†

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2026.

arXiv Project Page Highlight

FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation

Yuxuan Jiang, Zehua Chen, Zeqian Ju, Chang Li, Weibei Dou, Jun Zhu^†

ACM International Conference on Multimedia (ACM MM), 2025.

arXiv Project Page Oral