DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningDaya Guo, Junlong Li, Dejian Yang et al.|Nature|2025Cited by 610
DeepSeek-V3 Technical ReportDeepSeek-AI, Kexin Huang, Chong Ruan et al.|arXiv (Cornell University)|2024Cited by 239
DeepSeek LLM: Scaling Open-Source Language Models with LongtermismDeepSeek-AI, Zhangli Sha, Published by the European Mathematical Society with the support of the Schweizerische Akademie der Naturwissenschaften and the Stiftung zur Förderung der mathematischen Wissenschaften in der Schweiz. et al.|arXiv (Cornell University)|2024Cited by 90
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