Weixun Wang

~Weixun_Wang1

2

论文总数

1.0

年均投稿

4.7

平均评分

接收情况1/2

会议分布

COLM

1

ICLR

1

发表论文 (2 篇)

20251 篇

Adaptive dense reward:Understanding the Gap Between Action and Reward Space in Alignment

ICLR 2025withdrawn

20241 篇

The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization

COLM 2024Poster

合作者 (14)

Arian Hosseini1 篇

Kashif Rasul1 篇

Lewis Tunstall1 篇

Michael Noukhovitch1 篇

Shengyi Huang1 篇

Gengru Chen1 篇

Shaopan Xiong1 篇