Dr Roussel Nzoyem Ngueguin
PhD, MSc, BSc
Current positions
Honorary Research Associate
School of Engineering Mathematics and Technology
Contact
Press and media
Many of our academics speak to the media as experts in their field of research. If you are a journalist, please contact the University’s Media and PR Team:
Research interests
I'm interested in fundamental machine learning algorithms and their application to physical systems and sequence modelling. My research explores:
- Meta-learning for domain generalisation;
- Test-time training and parameter efficient fine-tuning;
- Generative models for sequential data;
- Physics-informed machine learning;
- Differentiable programming and optimal control.
For more information, please visit https://ddrous.github.io !
Publications
Recent publications
20/01/2026Language Models Do Not Embed Numbers Continuously
Proceedings of the 2nd AAAI Workshop on XAI4Science
Neural Context Flows for Meta-Learning of Dynamical Systems
13th International Conference on Learning Representations, ICLR 2025
Reevaluating Meta-Learning Optimization Algorithms Through Contextual Self-Modulation
Proceedings of The 4th Conference on Lifelong Learning Agents
MixER
Weight-Space Linear Recurrent Neural Networks
Weight-Space Linear Recurrent Neural Networks
Thesis
Learning to Learn Sequential Dynamics
Supervisors
Award date
09/12/2025


