Zilin Wang

Lady Margaret Hall, Oxford, UK

Hi there! I am a Computer Science Ph.D. student at the University of Oxford in the FLAIR and WhiRL labs. I am fortunated to be co-supervised by Professor Jakob Foerster and Professor Shimon Whiteson. I previously received a Master’s degree from Tsinghua University, supervised by Prof. Zhiyong Wu. Before that, I did my undergraduate at Dalian University of Technology.

My research focuses on developing general decision-making agents capable of interacting with complex and dynamic environments. Currently, I am exploring Deep Reinforcement Learning (Deep RL) as a core solution methodology.

In my sparse time, I enjoy running, hiking, badminton, and fitness, as well as anime and video games. Additionally, I am a ploy-glot, fluent in Mandarin, English, and Japanese. I love learning new languages because I believe a new language means a fresh perspective on this wonderful world!

CV / Google Scholar / Github / X / Linkedin

News

Oct 05, 2024	Starting my DPhil at Oxford! I’m so excited about my journey here!
Sep 18, 2024	I finished my research internship at Lingjun Investment, a quantitative fund. Greatly appreciating for this experience!
Jun 30, 2024	I graduated from Tsinghua University. It was an incredible and unforgettable journey. Love you forever, THU!
Dec 09, 2023	Our work Explore 3d dance generation via reward model from automatically-ranked demonstrations is accepted by AAAI 2024.
Jul 25, 2023	Our work UnifiedGesture, which proposed a new pipeline for gesture generation, got an oral at ACM MM 2023.
Jun 16, 2023	Our work Multi-Scale Speaker Extraction got an oral at Interspeech 2023.
Feb 16, 2023	Our work A Synthetic Corpus Generation Method for Neural Vocoder Training is accepted by ICASSP 2023.
Feb 16, 2022	Our work FullSubNet+, a new pipeline for speech enhancement, is accepted by ICASSP 2022.

Selected Publications

Notation * indicates equal contributions.

Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations

Zilin Wang^*, Haolin Zhuang^*, Lu Li^*, Yinmin Zhang, Junjie Zhong, and 4 more authors

In Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, February 20-27, 2024, Vancouver, Canada, 2024

Bib PDF Video Poster

@inproceedings{DBLP:conf/aaai/WangZLZZCYT024,
  author = {Wang, Zilin and Zhuang, Haolin and Li, Lu and Zhang, Yinmin and Zhong, Junjie and Chen, Jun and Yang, Yu and Tang, Boshi and Wu, Zhiyong},
  title = {Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations},
  booktitle = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI} 2024, February 20-27, 2024, Vancouver, Canada},
  pages = {301--309},
  publisher = {{AAAI} Press},
  year = {2024},
  webpage = {https://sites.google.com/view/e3d2},
}

UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons

Sicheng Yang^*, Zilin Wang^*, Zhiyong Wu, Minglei Li, Zhensong Zhang, and 6 more authors

In ACM Multimedia, 2023

Bib PDF Video Code Poster

@inproceedings{DBLP:conf/mm/YangW00ZHHXWYD23,
  author = {Yang, Sicheng and Wang, Zilin and Wu, Zhiyong and Li, Minglei and Zhang, Zhensong and Huang, Qiaochu and Hao, Lei and Xu, Songcen and Wu, Xiaofei and Yang, Changpeng and Dai, Zonghong},
  title = {UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons},
  year = {2023},
  pages = {1033-1044},
  url = {https://doi.org/10.1145/3581783.3612503},
  booktitle = {ACM Multimedia},
}

A Synthetic Corpus Generation Method for Neural Vocoder Training

Zilin Wang, Peng Liu, Jun Chen, Sipan Li, Jinfeng Bai, and 3 more authors

In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

Bib PDF Code Poster

@inproceedings{10094786,
  author = {Wang, Zilin and Liu, Peng and Chen, Jun and Li, Sipan and Bai, Jinfeng and He, Gang and Wu, Zhiyong and Meng, Helen},
  booktitle = {ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {A Synthetic Corpus Generation Method for Neural Vocoder Training},
  year = {2023},
  pages = {1-5},
  webpage = {https://zerlinwang.github.io/synthetic-corpus-vocoder/},
}

FullSubNet+: Channel Attention Fullsubnet with Complex Spectrograms for Speech Enhancement

Jun Chen, Zilin Wang, Deyi Tuo, Zhiyong Wu, Shiyin Kang, and 1 more author

In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022

Bib PDF Code

@inproceedings{9747888,
  author = {Chen, Jun and Wang, Zilin and Tuo, Deyi and Wu, Zhiyong and Kang, Shiyin and Meng, Helen},
  booktitle = {ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  title = {FullSubNet+: Channel Attention Fullsubnet with Complex Spectrograms for Speech Enhancement},
  year = {2022},
  pages = {7857-7861},
  keywords = {Time-frequency analysis;Convolution;Conferences;Noise reduction;Memory management;Speech enhancement;Feature extraction;speech enhancement;multi-scale time sensitive channel attention;phase information;full-band extractor},
  url = {https://ieeexplore.ieee.org/document/9747888},
  webpage = {https://rookiejunchen.github.io/fullsubnet-plus.github.io/},
}