作者位次 #2/4ICML 2026Poster· Deep Learning / Large Language Models
Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics
Raphael Bernas · Fanny Jourdan · Antonin Poché · Céline Hudelot
理论与学习动力学OpenReview
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。
Raphael Bernas · Fanny Jourdan · Antonin Poché · Céline Hudelot
Antonin Poché · Thomas Mullor · Gabriele Sarti · Frédéric Boisnard · Corentin Friedrich · Charlotte Claye · Francois Hoofd · Raphael Bernas · Nicholas Asher · Céline Hudelot · Fanny Jourdan
Interpreto is an open-source Python library for interpreting HuggingFace language models, from early BERT variants to LLMs. It provides two complementary families of methods: attribution methods and concept-based explanations. The library bridges recent research and practical tooling by exposing...