Chang Gao

~Chang_Gao1

3

论文总数

1.5

年均投稿

6.3

平均评分

接收情况2/3

会议分布

NeurIPS

2

ICLR

1

发表论文 (3 篇)

20251 篇

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

NeurIPS 2025Poster

20242 篇

StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving

NeurIPS 2024Poster

JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuning

ICLR 2024Rejected

合作者 (20)

Guizhen Chen1 篇

Wenxuan Zhang1 篇

Haiyun Jiang1 篇

Shuming Shi1 篇

Andrew Zhao1 篇