Mixture-of-Experts Language Models

Yu Wu's public homepage says he is a technical staff member at DeepSeek AI who leads the LLM Alignment Team and works on writing, QA, AI search, reasoning, and safety.

Researcher at DeepSeek AI working on decision-making and post-training for large language models.

Research scientist working on large language models and retrieval-augmented generation; creator of the open-source project tiny-universe.

Wangding Zeng is a researcher at DeepSeek. His OpenReview profile also lists graduate and undergraduate study at Beijing University of Posts and Telecommunications.

Research scientist at Ai2 and PhD candidate at the University of Washington. Her work focuses on language models, evaluation, and building practical open-source AI systems.

R. X. Xu is a research scientist at DeepSeek AI. His homepage says he works on trustworthy and efficient large language models, open-ended reasoning, and AI for healthcare.

DeepSeek team member and co-author of the DeepSeek-V3, DeepSeek-V2, and DeepSeek LLM technical reports.

Research engineer at DeepSeek-AI and co-author of the Nature paper introducing DeepSeek-R1.

DeepSeek team member and co-author of the DeepSeek-V3, DeepSeek-V2, and DeepSeek LLM technical reports.

DeepSeek report author whose DBLP publication record includes DeepSeek LLM, DeepSeekMoE, DeepSeek-V2, DeepSeek-V3, and DeepSeek-R1 work.

DeepSeek report author whose DBLP record includes DeepSeek LLM, DeepSeekMoE, DeepSeek-Coder-V2, DeepSeek-V3, and DeepSeek-R1 work.

Wenfeng Liang, also known as Liang Wenfeng, is linked to DeepSeek technical reports in LLMpeople and is identified in public references as the founder and CEO of DeepSeek.

Researcher at DeepSeek and former master's student in EECS at Peking University. Public profiles list work on LLMs, multimodal systems, transformers, BERT, and machine translation.

DeepSeek report author listed on DeepSeek LLM, DeepSeekMoE, DeepSeek-Coder, DeepSeek-V2, and DeepSeek-V3 reports, with report-backed work on large language models, mixture-of-experts systems, and code models.

Xingkai Yu is a report-backed author in the LLMpeople atlas, connected through DeepSeek technical reports including DeepSeek-V3, DeepSeek-V2, DeepSeek LLM, and DeepSeekMoE; his public GitHub profile lists DeepSeek affiliation.

Assistant professor at the University of California, Berkeley and research scientist at the Allen Institute for AI. Her public homepage highlights work on language models, natural language processing, pretraining, post-training, and test-time computation.

Y. K. Li is a report-backed author in the LLMpeople atlas, connected through 2 technical reports.

Researcher at Ai2 and coauthor of the EMO: Pretraining Mixture of Experts for Emergent Modularity.

Research scientist at DeepSeek with public GitHub projects spanning language models and AI systems.

Zhifang Sui is a report-backed author in the LLMpeople atlas, connected through DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.

Y. Wu

Huazuo Gao

Fuli Luo

Wangding Zeng

Akshita Bhagia

R. X. Xu

Panpan Huang

Chenggang Zhao

Jiashi Li

Damai Dai

Deli Chen

Wenfeng Liang

Chong Ruan

Zhenda Xie

Xingkai Yu

Sewon Min

Y. K. Li

Ryan Wang

Chengqi Deng

Zhifang Sui