Weiran Huang
 |
Weiran Huang (黄维然) |
About Me
I am an associate professor at Qing Yuan Research Institute of Shanghai Jiao Tong University, working on data-efficient machine learning algorithms and their applications. I earned my PhD in computer science from Institute for Interdisciplinary Information Sciences of Tsinghua University, where I had the honor of being supervised by Turing Award Laureate Prof. Andrew Yao and IEEE Fellow Dr. Wei Chen. Prior to that, I received my bachelor's degree in Electronic Engineering from Tsinghua University. Additionally, I was a visiting scholar hosted by Prof. Yaron Singer at Harvard SEAS.
My research interests are broadly in
Machine Learning Theory: Understanding the fundamental principles of machine learning, e.g., network capacity, optimization method and generalization ability, and providing insights for algorithms.
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.
Few-Shot Learning: Few-shot learning is the problem of making predictions on new tasks containing only a few samples with supervised information.
I am actively seeking self-motivated graduate students, as well as interns and postdocs, who are interested in joining our lab.
If you're interested, please email me your CV. Before reaching out, please carefully read our latest guidelines (招生须知).
Latest News
Oct 2023: Our paper “When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method” was among the ICCV 2023 Best Paper Finalists!
Sep 2023: Our paper “DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation” has been accepted by NeurIPS 2023!
Sep 2023: Our paper “FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning” has been accepted by NeurIPS 2023!
Sep 2023: I am honored to be selected as one of the 26 recipients of 2023 CCF-Baidu Open Fund!
Aug 2023: Our paper “InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4” has been covered by AI media Jiqi Zhixin (机器之心)!
Jul 2023: Our paper “When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method” has been accepted by ICCV 2023 as an oral presentation!
Apr 2023: Our paper “Rethinking Weak Supervision in Helping Contrastive Representation Learning” has been accepted by ICML 2023!
Jan 2023: Our paper “Towards the Generalization of Contrastive Self-Supervised Learning” has been accepted by ICLR 2023!
Jan 2023: Our paper “ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations” has been accepted by ICLR 2023!
Jan 2023: Our paper “Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding” has been accepted by ICLR 2023!
Dec 2022: I am excited to join the faculty at Shanghai Jiao Tong University as an Associate Professor!
Education & Work Experience
2012–2018: PhD in Computer Science, Tsinghua University (Advisor: Andrew Yao)
2009–2012: BSc in Electronic Engineering, Tsinghua University
2008–2009: Fundamental Science Class (数理基科班), Tsinghua University
2022/12–Present: Associate Professor at Shanghai Jiao Tong University
2018/07–2022/11: Research Scientist at Huawei Noah's Ark Lab (Director: Jun Yao)
2018/03–2018/06: Research Intern at Microsoft Research Asia (Mentor: Wei Chen)
2017/11–2018/02: Visiting Scholar at Harvard University (Advisor: Yaron Singer)
2015/08–2017/10: Research Intern at Microsoft Research Asia (Mentor: Wei Chen)
Awards & Honors
ICCV 2023 Best Paper Finalist for “When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method”, 2023.
Excellence in the Microsoft Research Asia Internship Program, 2018.
Outstanding Graduate Student, 2018.
Gold medal in the 24th Chinese Physics Olympiad (CPhO), Member of National Training Team (国家集训队, 31 people in China), 2007.
Services
Reviewer: ICML (2022-2023), NeurIPS (2019-2023), ICLR (2022-2024).