Changlong Yu

~Changlong_Yu1

3

论文总数

3.0

年均投稿

6.8

平均评分

接收情况3/3

会议分布

NeurIPS

2

ICML

1

发表论文 (3 篇)

20253 篇

Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models

NeurIPS 2025Poster

Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data

ICML 2025Poster

Ask a Strong LLM Judge when Your Reward Model is Uncertain

NeurIPS 2025Poster

合作者 (17)

Haoming Jiang3 篇

Ilgee Hong3 篇

Qingru Zhang2 篇

Zhenghao Xu2 篇