DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningDaya Guo, Junlong Li, Runxin Xu et al.|Nature|2025Cited by 610
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code IntelligenceDeepSeek-AI, Wenfeng Liang, Qihao Zhu et al.|arXiv (Cornell University)|2024Cited by 49
DeepSeek-V3.2: Pushing the Frontier of Open Large Language ModelsDeepSeek-AI, Jinhua Zhu, Aixin Liu et al.|arXiv (Cornell University)|2025Cited by 3