影响力指数

41.27/100

前 13.6%

全站排名 #8,728

发表论文3 篇

平均评分6.3

年均产出1.5 篇/年

Skander Moalla

PhD student@EPFL·瑞士·OpenReview

研究方向

LLM Alignment · Reinforcement Learning

Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions

NeurIPS 2025Poster

Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers

NeurIPS 2024Poster

No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO

NeurIPS 2024Poster

合作者 (6)

Caglar Gulcehre

博士导师3 篇