Yang Gao

~Yang_Gao6

3

论文总数

1.5

年均投稿

6.4

平均评分

接收情况3/3

会议分布

COLM

2

ICLR

1

发表论文 (3 篇)

20251 篇

RRM: Robust Reward Model Training Mitigates Reward Hacking

ICLR 2025Poster

20242 篇

Impact of Preference Noise on the Alignment Performance of Generative Language Models

COLM 2024Poster

Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data

COLM 2024Poster

合作者 (20)

Donald Metzler2 篇

Abe Ittycheriah1 篇

Anastasia Makarova1 篇

Aviral Kumar1 篇

Bilal Piot1 篇

Daniel Sohn1 篇

Jeremiah Zhe Liu1 篇