PeopleofSuperintelligence

Researcher

Wenjun Gao

Wenjun Gao is an artificial-intelligence researcher whose work spans open language models, formal theorem proving, training clusters and agent infrastructure. During 2024, he coauthored DeepSeek LLM, the mixture-of-experts models DeepSeek-V2, DeepSeek-Coder-V2 and DeepSeek-V3, the Lean 4 theorem prover DeepSeek-Prover-V1.5, and the Fire-Flyer AI-HPC cluster architecture. In 2025, he coauthored DeepSeek-Prover-V2 for formal theorem proving in Lean 4 and a Nature paper on the DeepSeek-R1 reinforcement-learning framework. As of October 2026, he is a coauthor of DeepSeek Elastic Compute (DSec), a September 2026 report on a production sandbox platform for large-scale agent training and evaluation.

Works
1
Citations
0
h-index
0

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. January 2024

    DeepSeek LLM

    In January 2024, he coauthors DeepSeek LLM, whose team uses supervised fine-tuning and Direct Preference Optimization to create the DeepSeek Chat models.

  2. May 2024

    DeepSeek-V2 mixture-of-experts model

    He coauthors DeepSeek-V2 in May 2024, a mixture-of-experts language model with 236B total parameters, 21B activated for each token, and a 128K-token context length.

  3. June 2024

    DeepSeek-Coder-V2 for code

    The June 2024 DeepSeek-Coder-V2 paper, which he coauthors, introduces an open-source mixture-of-experts code language model that matches GPT4-Turbo performance on code-specific tasks.

  4. August 2024

    DeepSeek-Prover-V1.5 and Fire-Flyer AI-HPC

    In August 2024, he coauthors DeepSeek-Prover-V1.5, an open-source language model for theorem proving in Lean 4 that improves on DeepSeek-Prover-V1 in training and inference. During August 2024, he also coauthors the Fire-Flyer AI-HPC paper on hardware-software co-design for deep learning, deploying the Fire-Flyer 2 cluster with 10,000 PCIe A100 GPUs.

  5. December 2024

    DeepSeek-V3 training

    With colleagues in December 2024, he coauthors DeepSeek-V3, a mixture-of-experts model with 671B total parameters and 37B activated for each token.

  6. April 2025

    DeepSeek-Prover-V2 for Lean

    His April 2025 work includes coauthoring DeepSeek-Prover-V2, an open-source language model for formal theorem proving in Lean 4, initialized with data from a recursive proof pipeline powered by DeepSeek-V3.

  7. September 2025

    DeepSeek-R1 reasoning

    In September 2025, he coauthors a Nature paper on DeepSeek-R1, whose reinforcement-learning framework develops self-reflection, verification and dynamic strategy adaptation in language models.

  8. As of October 2026

    DeepSeek Elastic Compute

    As of October 2026, he is a coauthor of DeepSeek Elastic Compute (DSec), a September 2026 report on a production sandbox platform for large-scale agent training and evaluation. Its unified SDK exposes FnCall, container, microVM and full-VM backends.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  2. The United States employs an estimated 48% of people shaping AIWe estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.
  3. 43% of living people shaping AI work outside their country of birthWe estimate that 43% of living people shaping AI work outside their country of birth (520 of 1,198 people with known birth and employment countries).
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionWe estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.

Sources and credits

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

  1. DeepSeek LLM: Scaling Open-Source Language Models with Longtermism arxiv.org. Checked 22 October 2026.
  2. [2405.04434] DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model arxiv.org. Checked 22 October 2026.
  3. [2406.11931] DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence arxiv.org. Checked 22 October 2026.
  4. DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search arxiv.org. Checked 22 October 2026.
  5. [2408.14158] Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning arxiv.org. Checked 22 October 2026.
  6. DeepSeek-V3 Technical Report arxiv.org. Checked 22 October 2026.
  7. DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition arxiv.org. Checked 22 October 2026.
  8. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning nature.com. Checked 22 October 2026.
  9. DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale arxiv.org. Checked 22 October 2026.
  10. Wenjun Gao | arXiv Science arxiv.science. Checked 22 October 2026.