Andrew Zhao
~Andrew_Zhao1
4
论文总数
2.0
年均投稿
平均评分
接收情况3/4
会议分布
NeurIPS
3
ICLR
1
发表论文 (4 篇)
20253 篇
3
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
NeurIPS 2025Spotlight
4
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
NeurIPS 2025Oral
4
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
NeurIPS 2025Poster