activity
20232026
collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

Efficient RL Training for LLMs with Experience Replay

Charles Arnal, Vivien Cabannes, Taco Cohen +2

While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL, it remains largely unexplore…

cs.LG2025

Provable Benefits of In-Tool Learning for Large Language Models

Sam Houliston, Ambroise Odonnat, Charles Arnal +1

Tool-augmented language models, equipped with retrieval, memory, or external APIs, are reshaping AI, yet their theoretical advantages remain underexplored. In this paper, we addres…

cs.LG2025

Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards

Charles Arnal, Gaëtan Narozniak, Vivien Cabannes +3

Reinforcement learning (RL) is increasingly used to align large language models (LLMs). Off-policy methods offer greater implementation simplicity and data efficiency than on-polic…

cs.LG2025

Easing Optimization Paths: a Circuit Perspective

Ambroise Odonnat, Wassim Bouaziz, Vivien Cabannes

Gradient descent is the method of choice for training large artificial intelligence systems. As these systems become larger, a better understanding of the mechanisms behind gradien…

cs.LG2024

A Mechanistic Study of Transformers Training Dynamics

Ambroise Odonnat, Wassim Bouaziz, Vivien Cabannes

Large-scale pretraining of transformers has been central to the success of foundation models. However, the scale of those models limits our understanding of the mechanisms at play…

cs.LG2024

Iteration Head: A Mechanistic Study of Chain-of-Thought

Vivien Cabannes, Charles Arnal, Wassim Bouaziz +3

Chain-of-Thought (CoT) reasoning is known to improve Large Language Models both empirically and in terms of theoretical approximation power. However, our understanding of the inner…