Jiahui GAO

Third-year Ph.D. candidate at HKU

github
linkedin
GoogleScholar

About Me

Hi! I am a third-year Ph.D. candidate of Department of Statistics and Actuarial Science (SAAS) in The University of Hong Kong (HKU), supervised by Stephen M.S. LEE and Yu Leung Ho Philip. I am also working closely and supervised by Lingpeng Kong from Department of Computer Science, HKU.

My current research interest is Natural Language Processing, including Pre-trained Language Modeling and Cross-modal(Vision-Language) Learning.

News

  • [Jan 2022] A paper gets accepted to ICLR-2022.
  • [Dec 2021] Two papers get accepted to AAAI-2022.
  • [May 2021] A paper gets accepted to ICML-2021.
  • [Aug 2019] Start Ph.D. journey in HKU.

Working Drafts

*indicates equal contribution

Self-Guided High-Quality Data Generation in Efficient Zero-Shot Learning
Jiahui Gao*, Renjie Pi*, Yong Lin, Hang Xu, Jiacheng Ye, Zhiyong Wu, Xiaodan Liang, Zhenguo Li, Lingpeng Kong. Preprint [arXiv]

ZeroGen: Efficient Zero-shot Learning via Dataset Generation
Jiacheng Ye*, Jiahui Gao*, Qintong Li, Hang Xu, Jiangtao Feng, Zhiyong Wu, Tao Yu, and Lingpeng Kong. Preprint [arxiv]

Pubulications

Revisiting Over-smoothing in BERT from the Perspective of Graph
Han Shi*, Jiahui Gao*, Hang Xu, Xiaodan Liang, Zhenguo Li, Lingpeng Kong, Stephen Lee, James T. Kwok.
International Conference on Learning Representations (ICLR-2022), Spotlight (rate: 5.19%). [arxiv]

AutoBERT-Zero: Evolving BERT Backbone from Scratch
Jiahui Gao, Hang Xu, Han Shi, Xiaozhe Ren, Philip LH Yu, Xiaodan Liang, Xin Jiang, Zhenguo Li.
Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22). [arxiv]

SparseBERT: Rethinking the Importance Analysis in Self-Attention
Shi Han, Jiahui Gao, Xiaozhe Ren, Hang Xu, Xiaodan Liang, Zhenguo Li, and James T. Kwok.
International Conference on Machine Learning (ICML-2021). Ÿ[arxiv]

UNISON: Unpaired Cross-Lingual Image Captioning
Jiahui Gao, Zhou Yi, Philip LH Yu, Shafiq Joty, and Jiuxiang Gu.
Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), Oral. [arxiv]

Detecting Comments Showing Risk for Suicide in YouTube
Jiahui Gao, Qijin Cheng and Philip LH Yu.
Proceedings of the Future Technologies Conference (FTC-2018). [arxiv]

Experiences

  • Remote research cooperation with Dr. Jiuxiang Gu from Adobe Research, Dec. 2019 - present.
  • Business Analyst (Full-time), Alibaba, Hangzhou, Aug. 2018 - Aug. 2019.
  • Business Analyst (Intern), Tencent, Shenzhen, Jun. 2017 - Aug. 2017.

Selected Honors

Teaching

  • STAT7102/7614: Advanced Statistical Modelling
Last Updated: 5/3/2022, 7:56:56 PM