Atlas / Reports / Detail
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Mathematical Reasoning Models report from DeepSeek with 8 connected researchers in the LLMpeople atlas.
Connected researchers
Researcher
6 reports
Runxin Xu
DeepSeek
Researcher at DeepSeek whose public homepage describes work on DeepSeek R1, V1, V2, V3, Math, Coder, and mixture-of-experts systems.
Researcher
11 reports
Daya Guo
DeepSeek / Moonshot AI
DeepSeek researcher focused on NLP, code intelligence, and LLM reasoning, with public work spanning DeepSeek-Coder, DeepSeekMath, DeepSeek-V2, DeepSeek-V3, and DeepSeek-R1.
Researcher
4 reports
Zhihong Shao
DeepSeek
Research scientist at DeepSeek AI working on multimodal large language models and end-to-end autonomous driving. Earned a PhD in computer science from the Chinese University of Hong Kong.
Researcher
8 reports
Qihao Zhu
DeepSeek
Research scientist focused on foundation models and multimodal large language models; his homepage notes earlier work at DeepSeek AI and current research at the University of Southern California.
Researcher
6 reports
Y. Wu
DeepSeek
Yu Wu is a researcher at DeepSeek AI and head of its LLM Alignment Team. His public homepage highlights work on reinforcement learning and alignment for the DeepSeek model family, including DeepSeek-V3, DeepSeek-R1, and DeepSeekMath, and notes prior work at Microsoft Research Asia.
Researcher
4 reports
Mingchuan Zhang
DeepSeek
Research scientist at DeepSeek interested in large language models, reinforcement learning, robot learning, and machine learning.
Researcher
8 reports
Junxiao Song
DeepSeek
Member of Technical Staff at DeepSeek.
Researcher
6 reports
Peiyi Wang
DeepSeek
Research scientist at DeepSeek with public GitHub projects on AI systems.