【deepseek】论文笔记--DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
DeepSeek-R1论文解析1.论文基本信息标题:DeepSeek-R1:IncentivizingReasoningCapabilityinLLMsviaReinforcementLearning作者:DeepSeek-AI团队(联系邮箱:research@deepseek.com)发表时间与出处:2024年,AIME2024(人工智能与数学教育国际会议)关键词:ReinforcementLe