PeopleofSuperintelligence

Researcher

Runji Wang

Runji Wang is a member of the DeepSeek-AI team in Hangzhou, China, and an author on several of the team's language-model reports. They were among the authors of the DeepSeek-V3 Technical Report in December 2024, which presents a Mixture-of-Experts model with 671B total parameters. The DeepSeek-R1 paper, posted to arXiv in January 2025 and published in Nature in September 2025, shows that the reasoning abilities of LLMs can be incentivized through pure reinforcement learning. They were also among the authors of the DeepSeek-V3.2 report in December 2025 and the DeepSeek-V4 preview report in April 2026. In September 2026, they were among the authors of DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts model that supports contexts of up to one million tokens.

Now at
DeepSeek
Works
6
Citations
1,965
h-index
4

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. December 2024

    The DeepSeek-V3 technical report

    In December 2024, they are among the authors of the DeepSeek-V3 Technical Report. The report presents a Mixture-of-Experts language model with 671B total parameters, 37B of them activated for each token, pre-trained on 14.8 trillion tokens.

  2. January 2025

    The DeepSeek-R1 preprint

    In January 2025, they are among the authors of DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning, posted to arXiv. The paper shows that the reasoning abilities of LLMs can be incentivized through pure reinforcement learning, with patterns such as self-reflection, verification and dynamic strategy adaptation emerging.

  3. September 2025

    DeepSeek-R1 in Nature

    In September 2025, Nature publishes the DeepSeek-R1 paper, titled "DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning", with them among the authors. Their affiliation is the DeepSeek-AI Team in Hangzhou, China.

  4. December 2025

    The DeepSeek-V3.2 report

    In December 2025, they are among the authors of DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models. The report introduces DeepSeek Sparse Attention, and its high-compute variant DeepSeek-V3.2-Speciale reaches gold-medal performance in both the 2025 International Mathematical Olympiad and the International Olympiad in Informatics.

  5. April 2026

    The DeepSeek-V4 preview

    In April 2026, they are among the authors of the preview report on the DeepSeek-V4 series. It describes DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated), both supporting a context length of one million tokens.

  6. September 2026

    DeepSeek-V4.1-Flash and KV caches

    In September 2026, they are among the authors of DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression. The report describes a multimodal Mixture-of-Experts model with 552B backbone parameters and support for contexts of up to one million tokens, with a global KV cache footprint of 890 bytes per token.

Most-cited works

  1. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning2025 · Nature · 1,118 citationsWith Bingxuan Wang, Chengqi Deng, Damai Dai, Daya Guo, Erhang Li and Fangyun Lin
  2. Can Open Large Language Models Catch Vulnerabilities?2025 · 539 citationsWith Bingxuan Wang, Chengqi Deng, Damai Dai, Erhang Li, Fangyun Lin and Haocheng Wang
  3. DeepSeek-V3 Technical Report2024 · 292 citationsWith Bingxuan Wang, Chengqi Deng, Damai Dai, Daya Guo, Dejian Yang and Erhang Li
  4. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models2025 · 19 citationsWith Chengqi Deng, Damai Dai, Daya Guo, Erhang Li, Fangyun Lin and Honghui Ding
  5. DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence2026 · 4 citationsWith Bingxuan Wang, Chengqi Deng, Damai Dai, Daya Guo, Erhang Li and Fangyun Lin

From OpenAlex, as of 21 October 2026.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Runji Wang. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes DeepSeek. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.
  3. 5,000 frontier users would be 38.2% of the core labs' 13,100 reported staffIncludes DeepSeek. 5,000 frontier users would be 38.2% of the core labs' 13,100 reported staff. We test the estimate against 3,913 named model contributors and dated all-staff records across Google DeepMind, OpenAI and Anthropic, plus six additional frontier-grade labs.
  4. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes DeepSeek. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

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

  1. [2412.19437] DeepSeek-V3 Technical Report arxiv.org. Checked 20 October 2026.
  2. [2501.12948] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning arxiv.org. Checked 20 October 2026.
  3. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning (Nature) nature.com. Checked 20 October 2026.
  4. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning (RePEc) ideas.repec.org. Checked 20 October 2026.
  5. [2512.02556] DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models arxiv.org. Checked 20 October 2026.
  6. [2606.19348] DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence arxiv.org. Checked 20 October 2026.
  7. [2609.19969] DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression arxiv.org. Checked 20 October 2026.