PeopleofSuperintelligence

Researcher

Honghui Ding

Honghui Ding is an AI researcher whose coauthored work tracks DeepSeek-AI's language models and agent-training systems. He coauthors DeepSeek LLM, DeepSeek-V2, and DeepSeek-V3 in 2024, then DeepSeek-R1 and DeepSeek-V3.2 in 2025. In 2026, he coauthors DeepSeek-V4 and DeepSeek-V4.1-Flash as the team extends context length and compresses KV caches. As of October 2026, he is affiliated with DeepSeek-AI and coauthors DeepSeek Elastic Compute, a production sandbox platform for agent training.

Timeline

  1. January 2024

    Scaling DeepSeek LLM

    In January 2024, he coauthors DeepSeek LLM, a project that studies scaling laws for open-source models in 7B and 67B configurations.

  2. May 2024

    DeepSeek-V2 MoE model

    In May 2024, he coauthors DeepSeek-V2, a mixture-of-experts model with 236 billion total parameters and 21 billion active for each token.

  3. December 2024

    DeepSeek-V3 technical report

    The December 2024 report lists him among its authors and presents DeepSeek-V3, a 671-billion-parameter mixture-of-experts model. Its architecture uses Multi-head Latent Attention and DeepSeekMoE.

  4. September 2025

    DeepSeek-R1 in Nature

    In September 2025, he coauthors the Nature paper DeepSeek-R1 with the DeepSeek-AI Team. The paper shows that pure reinforcement learning can incentivize reasoning in language models.

  5. December 2025

    DeepSeek-V3.2 and sparse attention

    In December 2025, he coauthors DeepSeek-V3.2, which pairs efficient long-context attention with a scalable reinforcement-learning framework for reasoning and agent performance.

  6. April 2026

    DeepSeek-V4 million-token context

    The April 2026 DeepSeek-V4 report lists him among DeepSeek-AI's authors and introduces V4-Pro and V4-Flash, two mixture-of-experts models that support one-million-token context windows.

  7. September 2026

    DeepSeek-V4.1-Flash compression

    In September 2026, he coauthors DeepSeek-V4.1-Flash, a multimodal mixture-of-experts model with 552 billion backbone parameters. The report targets memory and data-transfer costs from large key-value caches.

  8. As of October 2026

    DeepSeek-AI affiliation

    His September 2026 report lists DeepSeek-AI as his affiliation and introduces DeepSeek Elastic Compute (DSec), a production sandbox platform for large-scale agent training.

  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 Honghui Ding 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 incentivizes reasoning in LLMs through reinforcement learning nature.com. Checked 19 October 2026.
  5. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning ideas.repec.org. Checked 19 October 2026.
  6. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models arxiv.org. Checked 19 October 2026.
  7. DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence arxiv.org. Checked 19 October 2026.
  8. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression arxiv.org. Checked 19 October 2026.
  9. DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale arxiv.org. Checked 19 October 2026.