PeopleofSuperintelligence

Researcher

Wentao Zhang

Wentao Zhang is a researcher whose DeepSeek work spans language models, reasoning and inference. In 2024, he coauthored DeepSeek LLM, DeepSeek-Coder, DeepSeek-V2 and DeepSeek-V3. DeepSeek-R1, which he coauthored in 2025, reported that pure reinforcement learning could encourage language-model reasoning without human-labelled trajectories, while DeepSeek-V3.2's high-compute Speciale variant reached gold-medal performance at the 2025 IMO and IOI. He coauthored DSpark in July 2026 and is listed among the Research & Engineering contributors to DeepSeek-V4.1-Flash as of October 2026.

Now at
DeepSeek
Works
1

Publication numbers from OpenAlex, as of 22 October 2026. Citations and h-index are hidden because this OpenAlex record may be incomplete or mix in other authors.

Timeline

  1. 2024

    DeepSeek LLM training data

    In 2024, he coauthors DeepSeek LLM, an open-source language-model project whose training dataset contains 2 trillion tokens.

  2. 2024

    DeepSeek-Coder models

    In 2024, he coauthors DeepSeek-Coder, an open-source code-model series with sizes from 1.3B to 33B.

  3. May 2024

    DeepSeek-V2 and MoE

    In May 2024, he coauthors DeepSeek-V2, a mixture-of-experts language model with 236B total parameters and 21B activated for each token. It uses Multi-head Latent Attention and DeepSeekMoE.

  4. December 2024

    DeepSeek-V3 research credits

    In December 2024, he appears in DeepSeek-V3's Research & Engineering credits. DeepSeek-V3 has 671B total parameters and activates 37B for each token.

  5. 2025

    DeepSeek-R1 reasoning

    In 2025, he coauthors DeepSeek-R1, whose paper reports that pure reinforcement learning can encourage language-model reasoning without human-labelled trajectories.

  6. December 2025

    DeepSeek-V3.2 Speciale

    In December 2025, he coauthors DeepSeek-V3.2. Its high-compute Speciale variant reaches gold-medal performance at the 2025 IMO and IOI.

  7. July 2026

    DSpark speculative decoding

    In July 2026, he coauthors DSpark, a speculative-decoding framework that unifies high-throughput parallel generation with adaptive, load-aware verification.

  8. As of October 2026

    DeepSeek-V4.1-Flash credits

    As of October 2026, he appears among the Research & Engineering contributors to DeepSeek-V4.1-Flash.

  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 Wentao Zhang yet. Send us a free-licensed photo.

  1. DeepSeek LLM: Scaling Open-Source Language Models with Longtermism arxiv.org. Checked 22 October 2026.
  2. DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence arxiv.org. Checked 22 October 2026.
  3. GitHub - deepseek-ai/DeepSeek-Coder: DeepSeek Coder: Let the Code Write Itself github.com. Checked 22 October 2026.
  4. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model arxiv.org. Checked 22 October 2026.
  5. DeepSeek-V3 Technical Report arxiv.org. Checked 22 October 2026.
  6. DeepSeek-V3 Technical Report arxiv.org. Checked 22 October 2026.
  7. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning nature.com. Checked 22 October 2026.
  8. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models arxiv.org. Checked 22 October 2026.
  9. DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation arxiv.org. Checked 22 October 2026.
  10. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression arxiv.org. Checked 22 October 2026.