PeopleofSuperintelligence

Researcher

Ziwei Xie

As of October 2026, Ziwei Xie contributes to research and engineering at DeepSeek-AI, with work across language models, reasoning and agent training. He coauthored DeepSeek LLM, DeepSeek-V2 and DeepSeek-V3 in 2024. His 2025 papers include DeepSeek-R1's reinforcement-learning approach to reasoning and DeepSeek-V3.2's sparse attention and agent-task synthesis. In 2026, he coauthored DeepSeek-V4, whose two models support a context length of one million tokens, and DeepSeek Elastic Compute, a sandbox platform for agent training.

Now at
DeepSeek

Timeline

  1. January 2024

    Scaling DeepSeek LLM

    In January 2024, he coauthors DeepSeek LLM: Scaling Open-Source Language Models with Longtermism, which studies scaling laws for 7B and 67B models. Its findings address these two commonly used open-source configurations.

  2. May 2024

    DeepSeek-V2's 236B model

    In May 2024, he coauthors DeepSeek-V2, a mixture-of-experts model with 236B total parameters and 21B activated per token. Its architectures include Multi-head Latent Attention and DeepSeekMoE.

  3. December 2024

    DeepSeek-V3 technical report

    In December 2024, he coauthors DeepSeek-V3, a mixture-of-experts model with 671B total parameters and 37B activated per token. The model is pretrained on 14.8 trillion tokens.

  4. January 2025

    DeepSeek-R1 reasoning

    In January 2025, he coauthors DeepSeek-R1. The paper shows that pure reinforcement learning can incentivize reasoning without human-labeled reasoning trajectories.

  5. December 2025

    DeepSeek-V3.2 sparse attention

    In December 2025, he coauthors DeepSeek-V3.2, whose research and engineering methods include DeepSeek Sparse Attention, a scalable reinforcement-learning framework and a synthesis pipeline that generates training data for agentic tool use.

  6. 2026

    DeepSeek-V4 preview report

    In 2026, he coauthors DeepSeek-V4, a preview series of two mixture-of-experts models that support a context length of one million tokens.

  7. September 2026

    DeepSeek Elastic Compute

    In September 2026, he coauthors DeepSeek Elastic Compute (DSec), a production sandbox platform with FnCall, container, microVM and full-VM backends.

  8. As of October 2026

    Research and engineering at DeepSeek-AI

    As of October 2026, he is a research and engineering contributor at DeepSeek-AI.

  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 Ziwei Xie 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. README.md · deepseek-ai/DeepSeek-V3 huggingface.co. Checked 21 October 2026.
  5. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning arxiv.org. Checked 21 October 2026.
  6. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models arxiv.org. Checked 21 October 2026.
  7. DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence arxiv.org. Checked 21 October 2026.
  8. DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale arxiv.org. Checked 21 October 2026.
  9. Ziwei Xie | 500AI 500ai.org. Checked 21 October 2026.