PeopleofSuperintelligence

Researcher

Guowei Li

Guowei Li is a DeepSeek-AI researcher credited on language-model reports from 2024 to 2026. In 2024, he was named on the DeepSeek LLM and DeepSeek-V2 papers, then received Research & Engineering credit on DeepSeek-V3. He later coauthored the DeepSeek-R1 report on multi-stage reinforcement learning and DeepSeek-V3.2 on efficient reasoning and agent performance. As of October 2026, he is listed in the Research & Engineering credits for DeepSeek-V4.1-Flash, a multimodal model with 552B parameters and a one-million-token context.

Timeline

  1. January 2024

    DeepSeek LLM pretraining

    The January 2024 DeepSeek LLM paper lists him among DeepSeek-AI's authors. It presents open-source 7B and 67B language models and describes a 2-trillion-token pretraining dataset.

  2. May 2024

    DeepSeek-V2 mixture-of-experts

    DeepSeek-V2's May 2024 paper lists him among its authors. The mixture-of-experts model has 236B total parameters, activates 21B per token, and supports a 128K-token context.

  3. December 2024

    DeepSeek-V3 research credits

    The December 2024 DeepSeek-V3 technical report places him in its Research & Engineering credits. It presents a 671B-parameter mixture-of-experts model that activates 37B per token and uses Multi-head Latent Attention with DeepSeekMoE.

  4. 2025

    DeepSeek-R1 reasoning

    The January 2025 DeepSeek-R1 report lists him among its authors and describes a multi-stage pipeline that integrates rejection sampling, reinforcement learning, and supervised fine-tuning. The pipeline carries reasoning from DeepSeek-R1-Zero into R1 and aligns model behavior with human preferences through additional non-reasoning data. The 2025 Nature article lists him under the DeepSeek-AI Team.

  5. December 2025

    DeepSeek-V3.2 and agents

    DeepSeek-V3.2's December 2025 paper names him in its Research & Engineering credits. It introduces DeepSeek Sparse Attention and presents a model designed for efficient computation, reasoning, and agent performance.

  6. As of October 2026

    DeepSeek-V4.1-Flash credits

    As of October 2026, he is listed in the Research & Engineering credits for DeepSeek-V4.1-Flash. The report introduces a multimodal mixture-of-experts model with 552B backbone parameters and contexts up to one million tokens, focused on KV-cache compression.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

Sources and credits

Photo: We have no published photo of Guowei Li yet. Send us a free-licensed photo.

  1. DeepSeek LLM: Scaling Open-Source Language Models with Longtermism arxiv.org. Checked 19 October 2026.
  2. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model arxiv.org. Checked 19 October 2026.
  3. DeepSeek-V3 Technical Report arxiv.org. Checked 19 October 2026.
  4. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning arxiv.org. Checked 19 October 2026.
  5. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning alphaxiv.org. Checked 19 October 2026.
  6. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning ideas.repec.org. Checked 19 October 2026.
  7. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models arxiv.org. Checked 19 October 2026.
  8. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression arxiv.org. Checked 19 October 2026.