I am a Lecturer (Assistant Professor) in Computer Science at the University of Exeter, previously I worked at the Chinese Academy of Sciences and the University of Liverpool. I earned my PhD from the University of Liverpool, under the supervision of Prof. Xiaowei Huang and Prof. Xinping Yi.

I am interested in developing reliable (e.g., robust, generalisable, and efficient [NeurIPS20,CVPR22,23,ICCV23a,TIFS25,ICLR25a]) algorithms for modern machine learning models and applications [ICCV23b,AAAI23,ECCV24]. I focuse on aligning AI with human rules/preferences [ICML24,ICLR25b], with an emphasis on providing formal theoretical guarantees and rigorous statistical analyses [TMLR22,TPAMI25].

I am pleased to announce multiple openings for PhD and internship positions for the 2024/25 academic year. Scholarships are available through the University of Exeter and the CSC-Exeter program. If you are interested in these opportunities or would like to discuss potential collaborations, please don’t hesitate to contact me at g.jin@exeter.ac.uk.

Recent News

• (06/2025) One paper accepted to TMLR.
• (06/2025) One paper accepted to IEEE TPAMI.
• (05/2025) I will be serving as an Area Chair for NeurIPS 2025 (Position Paper Track).
• (04/2025) One paper accepted to IEEE TIFS.
• (02/2025) Get two PhD studentships from the EU Horizon project.
• (01/2025) Two papers accepted to ICLR 2025.
• (07/2024) Start my position as a Lecturer (Assistant Professor) at Exeter.
• (06/2024) One paper accepted to ECCV 2024.
• (01/2024) One paper accepted to ICML 2024.

Funding & Grants

• Robustifying Generative AI through Human-Centric Integration of Neural and Symbolic Methods (External Participant) 2025 - 2028
  Funded by EU Horizon.
• FOCETA (Foundations for Continuous Engineering of Trustworthy Autonomy) (Research Assistant) 2021 - 2023
  Funded by EU H2020.
• EnnCore (End-to-End Conceptual Guarding of Neural Architectures) (Research Assistant) 2020 - 2024
  Funded by EPSRC.
• SOLITUDE (Safety Argument for Learning-enabled Autonomous Underwater Vehicles) (Research Assistant) 2020 - 2022
  Funded by UK DSTL.

Selected Publications

Enhancing Robust Fairness via Confusional Spectral Regularization, ICLR 2025
Gaojie Jin, Sihao Wu, Jiaxu Liu, Tianjin Huang, Ronghui Mu

Enhancing Adversarial Training with Second-Order Statistics of Weights, CVPR 2022, IEEE TPAMI 2025
Gaojie Jin, Xinping Yi, Wei Huang, Sven Schewe, Xiaowei Huang

Invariant Correlation of Representation with Label, IEEE TIFS 2025
Gaojie Jin, Ronghui Mu, Xinping Yi, Xiaowei Huang, Lijun Zhang

Randomized Adversarial Training via Taylor Expansion, CVPR 2023
Gaojie Jin, Xinping Yi, Dengyu Wu, Ronghui Mu, Xiaowei Huang

How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks, NeurIPS 2020
Gaojie Jin, Xinping Yi, Liang Zhang, Lijun Zhang, Sven Schewe, Xiaowei Huang

Full list

Teaching

• ECM1416: Computational Mathematics

Textbook: Machine Learning Safety, Springer
Xiaowei Huang, Gaojie Jin, Wenjie Ruan

Academic Service

• Reviewer
  ICML, NeurIPS, ICLR, AISTATS, AAAI, CVPR, ICCV, ECCV, JMLR, IJCV, TMLR, TIFS, TDSC
• Area Chair
  NeurIPS 2025 (Position Paper Track)
• Organise the workshop TrustRL: Trustworthy in Reinforcement Learning at ATC 2024