Welcome!

I am a final-year PhD student in Machine Learning at Imperial College London, supervised by Yingzhen Li. I obtained my MPhil degree in Machine Learning and Machine Intelligence from the University of Cambridge in 2020, supervised by José Miguel Hernández-Lobato. Before that, I graduated with a BSc (Hons) in Mathematics and Statistics from McMaster University.

During my PhD, I mainly work on uncertainty quantification and robustness in large-scale deep sequence models (e.g., Transformers, RNNs), sequential learning, and deep generative models. In general, I am also interested in adaptive methods (e.g., continual learning). I aim to develop reliable algorithms with improved uncertainty calibration, robustness, and adaptation.

From August to December 2024, I worked on continual learning as a research intern in the Approximate Bayesian Inference team at RIKEN AIP in Tokyo with Mohammad Emtiyaz Khan. From June to November 2023, I worked as a research intern in the Responsible AI team at ByteDance Research in London, where I researched on machine learning fairness.


Publications

An up-to-date list of publications can be found on my Google Scholar profile.

*equal contribution

Preprint

  • Wenlong Chen*, Naoki Kiyohara*, Harrison Bo Hua Zhu*, Yingzhen Li. Recurrent Memory for Online Interdomain Gaussian Processes. ICLR 2025, FPI Workshop & AABI 2025, Workshop Track [link]
  • Wenlong Chen*, Wenlin Chen*, Lapo Rastrelli, Yingzhen Li. Your Image is Secretly the Last Frame of a Pseudo Video. ICLR 2025, DeLTa Workshop [link]
  • Yohan Jung*, Hyungi Lee*, Wenlong Chen*, Thomas Möllenhoff, Yingzhen Li, Juho Lee, Mohammad Emtiyaz Khan. Compact Memory for K-prior Based Continual Learning. AABI 2025, Workshop Track [link]
  • Wenlong Chen*, Bolian Li*, Ruqi Zhang, Yingzhen Li. Bayesian Computation in Deep Learning. Preprint 2025 (intended for the 2nd edition of the Handbook of Markov chain Monte Carlo) [link]

Conference

  • Wenlong Chen*, Yegor Klochkov*, Yang Liu. Post-hoc Bias Scoring Is Optimal For Fair Classification. ICLR 2024 (spotlight) [link]
  • Wenlong Chen, Yingzhen Li. Calibrating Transformers via Sparse Gaussian Processes. ICLR 2023 [link]
  • Andrew Campbell*, Wenlong Chen*, Vincent Stimper*, Jose Miguel Hernandez-Lobato, Yichuan Zhang. A Gradient Based Strategy for Hamiltonian Monte Carlo Hyperparameter Optimization. ICML 2021 [link]


Activities

Organizer

I have been involved in the organization of the workshop 2nd UNCV at ICCV 2023, and the weekly Computational Statistics and Machine Learning (CSML) Reading Group at Imperial College London

Reviewer

NeurIPS, ICML, AISTATS, TMLR, UNCV

Contact

Feel free to reach out to me at wenlong.chen21 (at) imperial.ac.uk