Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation
Kaiyuan Liu, Jiahao Mei, Hengyu Zhang, et al. "Moyun: A Diffusion-Based Model for Style-Specific Chinese Calligraphy Generation." ACM MM Workshop, 2025.
CV
Download CV (English) 下载简历 (中文)
Education
- M.S. in Computer Science, Shanghai Jiao Tong University, 2025.9 - 2028.3
- X-LANCE Lab, advised by Prof. Mengyue Wu and Prof. Kai Yu
- Research: AI for mental health, audio-EEG decoding, affective computing, multimodal generation
- B.E. in Computer Science, East China Normal University, 2021.9 - 2025.3
- ICALK Lab, advised by Prof. Daoguo Dong and Prof. Liang He
- Research: Controllable music generation, visual-audio cross-modal alignment
Work Experience
- Xiaomi Inc., XiaoAI PLUS · Speech Generation Team, 2026.1 - 2026.7
- Algorithm Engineer, advised by Heinrich Dinkel
- End-to-end mixed audio (speech, music, sound effects) generation research
- Alibaba Group, Tongyi Lab · NLI Team, 2024.1 - 2024.8
- Algorithm Engineer, advised by Yuning Wu and Ming Yan
- LLM creative writing evaluation benchmark & unified audio generation framework research
Publications
WritingBench: A Comprehensive Benchmark for Generative Writing
Yuning Wu, Jiahao Mei, Ming Yan, et al. "WritingBench: A Comprehensive Benchmark for Generative Writing." NeurIPS, 2025.
Dasheng AudioGen: A Unified Model for Generating Coherent Audio Scenes from Text
Jiahao Mei, Heinrich Dinkel, Yadong Niu, et al. "Dasheng AudioGen: A Unified Model for Generating Coherent Audio Scenes from Text." arXiv, 2025.
LARA-Gen: Enabling Continuous Emotion Control for Music Generation Models via Latent Affective Representation Alignment
Jiahao Mei, Xuenan Xu, Zeyu Xie, et al. "LARA-Gen: Enabling Continuous Emotion Control for Music Generation Models via Latent Affective Representation Alignment." arXiv, 2025.
UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities
Xuenan Xu*, Jiahao Mei*, Zihao Zheng, et al. "UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities." arXiv, 2025.
MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio
Xuenan Xu, Jiahao Mei, Chenliang Li, et al. "MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio." NAACL, 2025.
DashengTokenizer: One Layer is Enough for Unified Audio Understanding and Generation
Heinrich Dinkel, Xingwei Sun, Gang Li, Jiahao Mei, et al. "DashengTokenizer: One Layer is Enough for Unified Audio Understanding and Generation." arXiv, 2025.
TEAdapter: Supply Vivid Guidance for Controllable Text-to-Music Generation
Jialing Zou*, Jiahao Mei*, Xudong Nan, et al. "TEAdapter: Supply Vivid Guidance for Controllable Text-to-Music Generation." IEEE ICME, 2024.
EMID: An Emotional Aligned Dataset in Audio-Visual Modality
Jialing Zou*, Jiahao Mei*, Guangze Ye, et al. "EMID: An Emotional Aligned Dataset in Audio-Visual Modality." ACM MM Workshop, 2023.
Skills
- Languages: Mandarin (native), English (CET-6: 544), Japanese
- Programming: Python, C/C++, Shell
- Research: Audio generation, LLM evaluation, multimodal learning, diffusion models, flow matching
Awards & Honors
- Outstanding Graduate of Shanghai, 2024
- National Scholarship (CNY 10,000), ECNU 2/115, 2024
- Huaxin Scholarship (CNY 15,000), ECNU 3/115, 2024
- China International College Students’ Innovation Competition, Shanghai Gold Award (Team Leader), 2024
- China Collegiate Computing Contest - Network Challenge, National Third Prize (Team Leader), 2024
- National College Students’ E-commerce Competition, Shanghai First Prize (Team Leader), 2024
- Shanghai College Students’ Computer Application Competition, Third Prize (Team Leader), 2024
- ECNU Most Vibrant Project Award (Team Leader), 2024
- Nezha Scholarship (CNY 10,000), ECNU 2/115, 2023
- National Innovation & Entrepreneurship Training Program, Outstanding Completion & Paper (Team Leader), 2023
- “Huichuang Youth” Shanghai Cultural Creativity Exhibition, First Prize, 2023