Qichao Zhang

~Qichao_Zhang3

2

论文总数

2.0

年均投稿

6.4

平均评分

接收情况2/2

会议分布

NeurIPS

1

COLM

1

发表论文 (2 篇)

20252 篇

Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL

NeurIPS 2025Poster

Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation

COLM 2025Poster

合作者 (10)

Dongbin Zhao2 篇

Jiahao Lin2 篇

Linjing Li2 篇

Songjun Tu2 篇

Xiangyu Tian2 篇

Xiangyuan Lan2 篇

Dongmei Jiang1 篇