PeopleofSuperintelligence

Researcher

Ying He

Ying He is an artificial intelligence researcher at DeepSeek, the Hangzhou-based team behind the DeepSeek language models. They were among the authors of DeepSeek LLM in January 2024, DeepSeek-V2 in May 2024 and the DeepSeek-V3 Technical Report in December 2024, which presented a model with 671B total parameters. Their 2025 work included the DeepSeek-R1 paper, which Nature published in September 2025, and Insights into DeepSeek-V3, a May 2025 study of hardware-aware model co-design. They also co-authored DeepSeek-V3.2 in December 2025 and the DeepSeek-V4 preview in April 2026. In September 2026, they were among the authors of the DeepSeek-V4.1-Flash and DSec reports.

Now at
DeepSeek

Timeline

  1. January 2024

    The DeepSeek LLM paper

    In January 2024, they are among the authors of DeepSeek LLM: Scaling Open-Source Language Models with Longtermism, a study of scaling laws for open-source language models in 7B and 67B configurations.

  2. May 2024

    The DeepSeek-V2 model

    In May 2024, they are among the authors of DeepSeek-V2, a Mixture-of-Experts language model with 236B total parameters, 21B of them activated for each token, and a context length of 128K tokens.

  3. December 2024

    The DeepSeek-V3 report

    In December 2024, they are among the authors of the DeepSeek-V3 Technical Report, which presents a Mixture-of-Experts model with 671B total parameters and 37B activated for each token.

  4. January 2025–September 2025

    DeepSeek-R1 in Nature

    They are among the authors of DeepSeek-R1, posted on arXiv in January 2025 as a study of incentivizing reasoning in LLMs via reinforcement learning. Nature publishes the paper in September 2025 with the DeepSeek-AI Team in Hangzhou, China.

  5. May 2025

    Insights into DeepSeek-V3

    In May 2025, they co-author Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures. The paper uses DeepSeek-V3, trained on 2,048 NVIDIA H800 GPUs, to show how hardware-aware model co-design enables cost-efficient training and inference.

  6. December 2025

    DeepSeek-V3.2 with sparse attention

    In December 2025, they are among the authors of DeepSeek-V3.2, which introduces DeepSeek Sparse Attention (DSA), an attention mechanism that reduces computational complexity in long-context scenarios.

  7. April 2026

    DeepSeek-V4 preview models

    In April 2026, they are among the authors of the DeepSeek-V4 preview: DeepSeek-V4-Pro with 1.6T parameters and DeepSeek-V4-Flash with 284B parameters, both supporting a context length of one million tokens.

  8. As of October 2026

    Researcher at DeepSeek

    They are an artificial intelligence researcher at DeepSeek. In September 2026, they are among the authors of the DeepSeek-V4.1-Flash report on KV cache compression and of the DeepSeek Elastic Compute (DSec) report on a sandbox platform for agentic training.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes DeepSeek. 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.

Sources and credits

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

  1. DeepSeek LLM: Scaling Open-Source Language Models with Longtermism arxiv.org. Checked 21 October 2026.
  2. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model arxiv.org. Checked 21 October 2026.
  3. DeepSeek-V3 Technical Report arxiv.org. Checked 21 October 2026.
  4. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning arxiv.org. Checked 21 October 2026.
  5. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning | Nature nature.com. Checked 21 October 2026.
  6. Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures arxiv.org. Checked 21 October 2026.
  7. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models arxiv.org. Checked 21 October 2026.
  8. DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence arxiv.org. Checked 21 October 2026.
  9. Ying He - Wikidata wikidata.org. Checked 21 October 2026.
  10. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression arxiv.org. Checked 21 October 2026.
  11. DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale arxiv.org. Checked 21 October 2026.