作者位次 #2/3ICML 2026Poster· Social Aspects / Accountability, Transparency, and Interpretability
Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
Maxime Méloux · François Portet · Maxime Peyrard
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Maxime Méloux · François Portet · Maxime Peyrard
Xinhao Zhang · Xi Chen · François Portet · Maxime Peyrard
Recent work has demonstrated the promise of orchestrating large language models (LLMs) within evolutionary and agentic optimization systems. However, the mechanisms driving these optimization gains remain poorly understood. In this work, we present a large-scale study of LLM-guided evolutionary s...
Felix Herron · Solange Rossato · Alexandre Allauzen · François Portet
Modern automatic speech recognition (ASR) systems have been observed to function better for certain speaker groups (SGs) than others, despite recent gains in overall performance. One potential impediment to progress towards fairer ASR is a more nuanced understanding of the types of modeling error...