影响力指数

40.25/100

前 14.3%

全站排名 #9,181

发表论文6 篇

平均评分5.7

年均产出3.0 篇/年

Maxime Peyrard

Associate Professor@CNRS·法国·OpenReview

研究方向

Interpretability · Generative models · Causality · evaluation · LLMs · computational social science · semantics · summarization

Mechanistic Interpretability as Statistical Estimation: A Variance Analysis of EAP-IG

ICLR 2026Rejected

The Dead Salmons of AI Interpretability: The Need for a Statistical Inference Perspective

ICLR 2026Withdrawn

zip2zip: Inference-Time Adaptive Tokenization via Online Compression

NeurIPS 2025Poster

Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?

ICLR 2025Poster

EuroBERT: Scaling Multilingual Encoders for European Languages

COLM 2025Poster

Symbolic Autoencoding with Straight-Through Gradient Approximations

ICLR 2025Rejected

合作者 (20)

François Portet

博后导师2 篇

Michael Gastpar