Weiran Huang (Chinese: 黄维然) is currently a researcher at the AI Theory Group of Noah's Ark Lab. He received his PhD degree in computer science from IIIS at Tsinghua University, under the supervision of Turing Award winner Prof. Andrew Yao and IEEE Fellow Dr. Wei Chen. He was a visiting scholar at Harvard University hosted by Dr. Yaron Singer, and also served as a research intern at Microsoft Research Asia. Before that, he got his BE degree from EE at Tsinghua University. In 2007, he won a gold medal in the 24th Chinese Physics Olympiad (CPhO), and was chosen to the National Training Team (国家集训队). His work has been published on top conferences such as NeurIPS, CVPR, ICCV, KDD, AAAI, IJCAI, etc. He served as a PC or reviewer for NeurIPS, ICLR, COLT, CVPR, ICCV, AAAI, IJCAI, etc.


  • Excellence in the Microsoft Research Asia Internship Program, 2018. [Media Coverage]
  • Outstanding Graduate Student, 2018. [Media Coverage]
  • Excellent Student Leader of Tsinghua, President of IIIS Student Union, 2013. [Media Coverage]
  • Tsinghua-Baidu Scholarship, Tsinghua Social Work Scholarship, Tsinghua Freshman Scholarship, 2008–2013.
  • Top 2 in Tsinghua Mathematical Contest in Modeling, 2012.
  • Excellent work in the Tencent Internet Development Competition, 2012.
  • Invited to the 11th Wu Chien-Shiung Science Camp, and won Osheroff Prize, 2008. [Media Coverage]
  • 1st Prize (gold medal) in the 24th Chinese Physics Olympiad (CPhO), and chosen to the National Training Team (31 people in China), 2007. [Media Coverage]

Research Interests

  • Machine Learning Theory: Learning theory aims to understand the fundamental principles of machine learning (e.g., network capacity, optimization method and generalization ability), and guide the design of new algorithms and frameworks.
  • Self-Supervised Learning: Self-supervised learning aims to pre-train a powerful feature extractor through a self-supervised task using a large amount of unlabeled data, such that the learned image representations can be efficiently adapted to downstream tasks.
P.S. We are constantly looking for self-motivated research interns. Please send me your CV if you are interested. (See Details)


  • Jiaye Teng*, Weiran Huang* and Haowei He*, Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis, arXiv:2103.03568, 2021. [paper] [more]
  • Kai Zheng, Tianle Cai, Weiran Huang, Zhenguo Li and Liwei Wang, Locally Differentially Private (Contextual) Bandits Learning, NeurIPS, 2020. [paper] [code] [more]
  • Aoxue Li, Weiran Huang, Xu Lan, Jiashi Feng, Zhenguo Li and Liwei Wang, Boosting Few-Shot Learning With Adaptive Margin Loss, CVPR, 2020. [paper] [more]
  • Yimin Huang, Weiran Huang, Liang Li and Zhenguo Li, Meta-Learning Pac-Bayes Priors in Model Averaging, AAAI, 2020. [paper] [more]
  • Jiacheng Sun, Xiangyong Cao, Hanwen Liang, Weiran Huang, Zewei Chen and Zhenguo Li, New Interpretations of Normalization Methods in Deep Learning, AAAI, 2020. [paper] [more]
  • Hanwen Liang, Shifeng Zhang, Jiacheng Sun, Xingqiu He, Weiran Huang, Kechen Zhuang and Zhenguo Li, Darts+: Improved Differentiable Architecture Search With Early Stopping, arXiv:1909.06035, 2019. [paper] [media coverage] [more]
  • Aoxue Li, Tiange Luo, Tao Xiang, Weiran Huang and Liwei Wang, Few-Shot Learning With Global Class Representations, ICCV, 2019. [paper] [code] [more]
  • Chang Xu, Weiran Huang, Hongwei Wang, Gang Wang and Tie‑Yan Liu, Modeling Local Dependence in Natural Language With Multi-Channel Recurrent Neural Networks, AAAI, oral paper, 2019. [paper] [more]
  • Xiaowei Chen, Weiran Huang, Wei Chen and John CS Lui, Community Exploration: From Offline Optimization to Online Learning, NeurIPS, 2018. [paper] [more]
  • Lichao Sun, Weiran Huang, Philip S Yu and Wei Chen, Multi-Round Influence Maximization, KDD, oral paper (AR: 10.9%), 2018. [paper] [more]
  • Weiran Huang, Jungseul Ok, Liang Li and Wei Chen, Combinatorial Pure Exploration With Continuous and Separable Reward Functions and Its Applications, IJCAI, 2018. [paper] [more]
  • Weiran Huang, Liang Li and Wei Chen, Partitioned Sampling of Public Opinions Based on Their Social Dynamics, AAAI, 2017. [paper] [more]
*Equal contribution authors. (The above list is generated from the .bib file.)


  • Invited Talks:
    • Invited Talk: "Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data?", Department of Computer Science & Technology, Nanjing Univeristy, Jun 2021.
    • Panelist: "Self-Supervised Learning", The 2021 BAAI Conference, Beijing, Jun 2021.
    • Speaker: "Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data?", The 2021 BAAI Conference, Beijing, Jun 2021.
    • Speaker: "Locally Differentially Private Bandits Learning", Industrial Video Intelligence Summit & Machine Learning Workshop, Nov 2020.
  • Professional Services:
    • Conference Reviewer: ICLR 2021, NeurIPS 2021, ICCV 2021, CVPR 2021, AAAI 2021 (PC), NeurIPS 2020, IJCAI 2020 (PC), ASONAM 2020 (PC), NeurIPS 2019, ASONAM 2019 (PC), COLT 2019, WINE 2017, NIPS 2016.
    • Journal Reviewer: JASIST.
  • Interns & Students:
    • Xuyang Zhao (PhD, Peking University)
    • Mingyang Yi (PhD, Chinese Academy of Sciences)
    • Jiaye Teng (PhD, Tsinghua University)
    Past: Yuxuan She (PhD, Peking University), Aoxue Li (PhD, Peking University), Peibin Chen (MS, Peking University), Yihong Chen (MS, Tsinghua University), Shifeng Zhang (PhD, Tsinghua University), Yue Liu (PhD, Peking University), Xingqiu He (PhD, University of Electronic Science and Technology of China), Yimin Huang (PhD, Peking University), Junyang Li (MS, Peking University).