2 citations · 5 across the 6 of their papers we have counts for
6 papers
Improving LLM-Generated Code Quality with GRPO
Maxime Robeyns, Laurence Aitchison
Large Language Models (LLMs) are gaining widespread use for code generation. Recent training procedures use execution feedback as a reward signal, typically focusing on the functio…
A Self-Improving Coding Agent
Maxime Robeyns, Martin Szummer, Laurence Aitchison
Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code th…
Bayesian Reward Models for LLM Alignment
Adam X. Yang, Maxime Robeyns, Thomas Coste +4
To ensure that large language model (LLM) responses are helpful and non-toxic, a reward model trained on human preference data is usually used. LLM responses with high rewards are…
Bayesian Low-rank Adaptation for Large Language Models
Adam X. Yang, Maxime Robeyns, Xi Wang +1
Low-rank adaptation (LoRA) has emerged as a new paradigm for cost-efficient fine-tuning of large language models (LLMs). However, fine-tuned LLMs often become overconfident especia…
Taylor TD-learning
Michele Garibbo, Maxime Robeyns, Laurence Aitchison
Many reinforcement learning approaches rely on temporal-difference (TD) learning to learn a critic. However, TD-learning updates can be high variance. Here, we introduce a model-ba…
A theory of representation learning gives a deep generalisation of kernel methods
Adam X. Yang, Maxime Robeyns, Edward Milsom +3
The successes of modern deep machine learning methods are founded on their ability to transform inputs across multiple layers to build good high-level representations. It is theref…