Electronics, Electrical Engineering and Computer Science
School of Electronics, Electrical Engineering and Computer Science
- Location
- Belfast, United Kingdom
- Funding
- See university guidance
- Application deadline
- See university guidance
About the project
My research studies how machine learning systems can remain reliable when information is imperfect. I have developed methods for learning from noisy, coarse and incomplete supervision, and now increasingly focus on evaluating and certifying foundation models when predictions or evaluators are unreliable. My interests include robust statistical evaluation, AI safety, computer vision and multimodal learning, with applications in healthcare, medical imaging and other scientific settings.
- Dr Chen Feng: School of Electronics, Electrical Engineering and Computer Science
Contact info
- View Academic Profile
- c.feng@qub.ac.uk
Research Interests
I welcome PhD applications in machine learning, artificial intelligence and computer vision, particularly in the following areas:
1. Robust Machine Learning: Learning from noisy, incomplete, coarse or weak supervision; representation learning; robustness under distribution shifts.
2. AI Safety and Reliability: Safety evaluation, adversarial robustness, uncertainty quantification, statistical guarantees and certification for large language models, multimodal foundation models and AI agents.
3. Foundation Models and Multimodal AI: Reliable learning and reasoning with large language, vision and multimodal models, including applications in computer vision and intelligent systems.
4. AI for Science and Real-World Applications: Developing reliable machine learning methods for scientific and practical problems, including healthcare, medical imaging, materials science and other domains with imperfect data.
Projects may involve theoretical foundations, new machine learning methods or interdisciplinary applications.
I welcome enquiries from motivated applicants with strong interests in these areas. Prospective students are encouraged to contact me by emails. Please keep your email concise and include three key details:
(1) if your university is outside the UK or China, it might be highly possible that I may be less familiar with the institutions. Please share its national ranking (with a source) or your university entrance examination rank or percentile;
(2) your publications in leading CORE A/A conferences or JCR-Q1 journals, with paper links;
(3) any funding you have secured (or self-funded) and the specific scholarships you intend to apply for. Full scholarships are highly competitive and require an exceptionally strong application.
Please email me using the subject line: [Prospective Student/Visitor] Your Name – Your Current Institution. Without this standard subject format, I may overlook your message, as I rely on these keywords to sort incoming emails.
Make a PhD enquiry
Current Research Opportunities
- Safety, Interpretability and Robustness of Foundation Models
- Learning from Imperfect Data for Real-World AI Applications
Public outreach & key achievements
I lead the QUB Machine Learning Lab, established in September 2025. My research has been published at leading international conferences and journals, including ICLR, CVPR, NeurIPS, AAAI and TMLR. I serve as an Associate Editor of IEEE Computational Intelligence Letters and actively contribute to international conference and workshop organisation including NeurIPS, BMVC, ICME and ICASSP.
- Personal Website: https://mrchenfeng.github.io/
- Research Lab: https://qub-ml.github.io/
- Google Scholar: https://scholar.google.com/citations?user=4VZhTYgAAAAJ
- GitHub: https://github.com/MrChenFeng
- ORCID: https://orcid.org/0000-0001-9199-559X
Research students
PhD Title | Safety and Reliability of Large Language and Multimodal Models
Name | Zhengli Shi
Years of study | 2026 - present
PhD Title | Foundation Models for Multimodal Data
Name | Zihan Xu
Years of study | 2026 - present
PhD Title | Causal Representation Learning
Name | Tadiyos Hailemichael Mamo
Years of study | 2025 - present
Discover More
- Faculty of Engineering and Physical Science
- School of Electronics, Electrical Engineering and Computer Science
- Centre for Intelligent Sustainable Computation