PeopleofSuperintelligence

Researcher

Xin Xie

Xin Xie is a researcher whose DeepSeek work spans language, code, vision-language and reasoning models. They coauthored reports on DeepSeek LLM, DeepSeek-V2, DeepSeek-Coder-V2, DeepSeek-VL2 and DeepSeek-V3 in 2024, then DeepSeek-R1 and DeepSeek-V3.2 in 2025. In September 2026, they coauthored DeepSeek-V4.1-Flash, whose global KV-cache footprint is 890 bytes per token.

Now at
DeepSeek

Timeline

  1. January 2024

    Scaling DeepSeek LLM

    In January 2024, they coauthor DeepSeek LLM, a study of scaling open-source language models. Its pre-training dataset contains 2 trillion tokens.

  2. May 2024

    DeepSeek-V2 language model

    In May 2024, they coauthor DeepSeek-V2, a mixture-of-experts language model with 236B total parameters and 21B active per token. It supports a context length of 128K tokens.

  3. June 2024

    DeepSeek-Coder-V2 code model

    In June 2024, they coauthor DeepSeek-Coder-V2; it expands programming-language support from 86 to 338 languages.

  4. December 2024

    DeepSeek-VL2 vision-language model

    In December 2024, they coauthor DeepSeek-VL2, which uses dynamic tiling for high-resolution images. The DeepSeek-VL2-Tiny, DeepSeek-VL2-Small and DeepSeek-VL2 variants have 1.0B, 2.8B and 4.5B activated parameters, respectively.

  5. December 2024

    DeepSeek-V3 technical report

    DeepSeek-V3 appears in December 2024 as a 671B mixture-of-experts model with 37B parameters active per token; they coauthor its technical report.

  6. September 2025

    DeepSeek-R1 reasoning paper

    In September 2025, they coauthor the DeepSeek-R1 paper as a member of the DeepSeek-AI Team. The paper describes self-reflection, verification and dynamic strategy adaptation under pure reinforcement learning.

  7. December 2025

    Sparse attention in V3.2

    DeepSeek-V3.2 introduces DeepSeek Sparse Attention in December 2025 to reduce computation in long-context scenarios. They coauthor the report.

  8. September 2026

    KV-cache compression in V4.1-Flash

    In September 2026, they coauthor DeepSeek-V4.1-Flash under the DeepSeek-AI group byline. Its design reduces the global KV-cache footprint to 890 bytes per token.

  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.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Xin 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-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence arxiv.org. Checked 21 October 2026.
  4. DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding arxiv.org. Checked 21 October 2026.
  5. deepseek-ai/deepseek-vl2 huggingface.co. Checked 21 October 2026.
  6. DeepSeek-V3 Technical Report arxiv.org. Checked 21 October 2026.
  7. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning ideas.repec.org. Checked 21 October 2026.
  8. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models arxiv.org. Checked 21 October 2026.
  9. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression arxiv.org. Checked 21 October 2026.