Scholar
Maxime Robeyns
Google Scholar ID: PRnvb5wAAAAJ
PhD Student, University of Bristol
Citations & Impact
Citations
186
H-index
4
i10-index
4
Publications
8
Co-authors
0
Contact
Publications
Resume
Academic Achievements
- Improving LLM-Generated Code Quality with GRPO
- A Self-Improving Coding Agent
- Bayesian Reward Models For LLM Alignment
- Bayesian Low-rank Adaptation for Large Language Models
- Taylor TD-learning
- A Theory of Representation Learning in Deep Neural Networks Gives a Deep Generalisation of Kernel Methods
- Fast Estimation of Physical Galaxy Properties using Simulation-Based Inference
Research Experience
- Founding engineer at iGent AI, a startup focused on autonomous AI software engineering and research agents.
Education
- Insufficient information
Background
- A final-year PhD student in machine learning, interested in using probabilistic machine learning for machine reasoning and decision making. Specifically, how to effectively train, fine-tune or continually update models; how to model arbitrary and complex distributions with neural density estimation; and how to reliably account for uncertainty and risk in model predictions.
Miscellany
- Writes articles related to work, including 'Weight-Init Conditioned Bayesian Neural Network Priors', 'Bayesian Low-Rank Adaptation for Large Language Models', and 'Second-Order Methods in Machine Learning'.