My research interests span robust machine learning, uncertainty estimation, out-of-distribution detection, and out-of-distribution generalization. More generally, I am interested in problems that machine learning faces when we deploy it in the real-world applications, e.g., large-scale annotation, AI alignment, small-data tasks. My PhD research falls mainly in the intersection of these ML problems and computer vision.
Before my PhD studies, I completed my MSc in CS at University of Oxford (supervisor: Prof. Yarin Gal) and my BSc in Math at Peking University (supervisor: Prof. Bin Dong). I have also worked as a researcher for a year at Megvii (previously known as Face++), studying large-scale annotation and OoD detection methods.
My CV is here.
- University of Tübingen, Germany (Jan. 2022 - Now)
- Ph.D, Computer Science
- Advisor: Andreas Geiger and Dan Zhang
- University of Oxford, UK (Oct. 2020 - Sept. 2021)
- M.S., Computer Science (Distinction)
- Advisor: Yarin Gal
- Peking University, China (Sept. 2015 - June 2019)
- B.S., Computing Mathematics
- Megvii Technology Inc, Beijing, China, (Feb. 2019 - Sept. 2020)
- ML Researcher, Data Research Group
- Research projects: Large-scale data annotation, out-of-distribution detection, few-shot learning
- Group leader: Xinyu Zhou
Preprints and Publications
- Decomposing Representations for Deterministic Uncertainty Estimation
- Haiwen Huang, Joost van Amersfoort, Yarin Gal
- 6th Bayesian Deep Learning workshop at NeurIPS 2021.
- Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
- Lewis Smith, Joost van Amersfoort, Haiwen Huang, Stephen Roberts, Yarin Gal
- Feature Space Singularity for Out-of-distribution Detection
- Nostalgic Adam: Weighing more of the past gradients when designing the adaptive learning rate
- Haiwen Huang, Chang Wang and Bin Dong
- IJCAI 2019.