影响力指数

20.22/100

前 41.1%

全站排名 #26,431

发表论文5 篇

平均评分4.3

年均产出1.7 篇/年

Michał Krutul

PhD student@University of Warsaw·波兰·OpenReview

$\mu$-Parameterization for Mixture of Experts

ICLR 2026Withdrawn

Projected Compression: Trainable Projections for Efficient Transformer Compression

ICLR 2026Withdrawn

Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient

ICML 2025Poster

Different Rates for Different Weights: Decoupled Relative Learning Rate Schedules

ICLR 2025Withdrawn

合作者 (17)

Jan Ludziejewski

Sebastian Jaszczur

Jakub Krajewski

Jan Małaśnicki

Kamil Adamczewski

Maciej Stefaniak