PeopleofSuperintelligence

Researcher

Xiaotao Nie

Xiaotao Nie is an artificial-intelligence researcher whose coauthored DeepSeek papers span open language models, AI computing clusters, mixture-of-experts architectures, and reinforcement-learning methods for reasoning. In 2024, he coauthored DeepSeek LLM, DeepSeek-V2, the Fire-Flyer AI-HPC cluster design, and the 671-billion-parameter DeepSeek-V3 model. His 2025 research included DeepSeek-R1, published in Nature on incentivizing reasoning through pure reinforcement learning, and DeepSeek-V3.2. In 2026, he coauthored the million-token DeepSeek-V4 preview series and the multimodal DeepSeek-V4.1-Flash model for KV-cache compression.

Works
8
Citations
2,087
h-index
6

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. January 2024

    DeepSeek LLM research

    In January 2024, he coauthors DeepSeek LLM, an open-source language model family with 7B and 67B configurations trained on a dataset of two trillion tokens. Its 67B Chat model surpasses GPT-3.5 in open-ended evaluations.

  2. May 2024

    The DeepSeek-V2 model

    He coauthors DeepSeek-V2 in May 2024, a 236-billion-parameter mixture-of-experts language model that activates 21 billion parameters per token across a 128,000-token context length. Its architecture combines Multi-head Latent Attention with DeepSeekMoE.

  3. August 2024

    Fire-Flyer AI-HPC cluster design

    In August 2024, he coauthors the Fire-Flyer AI-HPC paper on DeepSeek-AI's software-hardware co-design for deep learning. Deployed with 10,000 PCIe A100 GPUs, the Fire-Flyer 2 cluster approaches DGX-A100 performance while cutting costs in half and reducing energy consumption by 40 percent.

  4. December 2024

    The DeepSeek-V3 model

    With the DeepSeek-AI team in December 2024, he coauthors DeepSeek-V3, a 671-billion-parameter mixture-of-experts language model that activates 37 billion parameters for each token.

  5. January–September 2025

    DeepSeek-R1 reasoning

    He coauthors the DeepSeek-R1 technical report in January 2025 and the peer-reviewed edition in Nature in September 2025. The framework uses pure reinforcement learning to incentivize reasoning in language models and develop advanced reasoning patterns without human-labelled reasoning trajectories.

  6. December 2025

    The DeepSeek-V3.2 model

    In December 2025, he coauthors DeepSeek-V3.2, an open large language model that pairs high computational efficiency with reasoning and agent performance.

  7. April 2026

    The DeepSeek-V4 preview series

    His April 2026 work includes a preview of the DeepSeek-V4 series, presenting two mixture-of-experts language models built for million-token context intelligence.

  8. September 2026

    DeepSeek-V4.1-Flash research

    In September 2026, he coauthors DeepSeek-V4.1-Flash, a multimodal mixture-of-experts model with 552 billion backbone parameters that supports contexts of up to one million tokens. The model introduces a causal encoder-decoder architecture to compress the KV cache and reduce its footprint.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  2. The United States employs an estimated 48% of people shaping AIWe estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.
  3. 43% of living people shaping AI work outside their country of birthWe estimate that 43% of living people shaping AI work outside their country of birth (520 of 1,198 people with known birth and employment countries).
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionWe estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.

Sources and credits

Photo: We have no published photo of Xiaotao Nie 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-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model arxiv.org. Checked 22 October 2026.
  3. Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning arxiv.org. Checked 22 October 2026.
  4. DeepSeek-V3 Technical Report arxiv.org. Checked 22 October 2026.
  5. DeepSeek-V3 Technical Report | alphaXiv alphaxiv.org. Checked 22 October 2026.
  6. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 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. DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence arxiv.org. Checked 22 October 2026.
  10. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression arxiv.org. Checked 22 October 2026.