31 citations · 31 across the 5 of their papers we have counts for
5 papers
Policy Gradient Steering: Interventions from Behavioral Objectives
Yoann Poupart, Aurélie Beynier, Nicolas Maudet
Activation steering has emerged in large language models as a lightweight alternative for dynamically changing a model's behavior at inference time. However, we show that existing…
TDHook: A Lightweight Framework for Interpretability
Yoann Poupart
Interpretability of Deep Neural Networks (DNNs) is a growing field driven by the study of vision and language models. Yet, some use cases, like image captioning, or domains like De…
Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning
Yoann Poupart, Aurélie Beynier, Nicolas Maudet
Multi-Agent Deep Reinforcement Learning (MADRL) was proven efficient in solving complex problems in robotics or games, yet most of the trained models are hard to interpret. While l…
Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents
Yoann Poupart
AI led chess systems to a superhuman level, yet these systems heavily rely on black-box algorithms. This is unsustainable in ensuring transparency to the end-user, particularly whe…
Topology-driven ordering of flocking matter
Amélie Chardac, Ludwig A. Hoffmann, Yoann Poupart +2
When interacting motile units self-organize into flocks, they realize one of the most robust ordered state found in nature. However, after twenty five years of intense research, th…