PeopleofSuperintelligence

Researcher

Yuduan Wang

Yuduan Wang is a DeepSeek-AI research coauthor on reports about language models, reasoning and long-context systems. They coauthored DeepSeek-V2 in May 2024 and DeepSeek-V3 in December 2024; V3 has 671 billion total parameters and 37 billion activated for each token. In 2025, they coauthored DeepSeek-R1 on reinforcement-learning reasoning and DeepSeek-V3.2 on sparse attention. In April and September 2026, they coauthored DeepSeek-V4 and DeepSeek-V4.1-Flash, a multimodal model that supports million-token contexts and combines cross-layer KV-cache reuse with FP4 caching. They are a PhD student in the Hou Research Group at the National University of Singapore from 2022 to 2026.

Now at
DeepSeek
Badges

Timeline

  1. May 2024

    DeepSeek-V2 MoE model

    In May 2024, they coauthor DeepSeek-V2, a mixture-of-experts language model with 236 billion parameters, designed for economical training and efficient inference.

  2. December 2024

    DeepSeek-V3 MoE model

    In December 2024, they coauthor DeepSeek-V3, an MoE language model with 671 billion total parameters and 37 billion activated for each token.

  3. January 2025

    DeepSeek-R1 reasoning model

    In January 2025, they coauthor DeepSeek-R1, whose pure reinforcement-learning method encourages reasoning patterns such as self-reflection and verification.

  4. December 2025

    DeepSeek-V3.2 sparse attention

    In December 2025, they coauthor DeepSeek-V3.2, which introduces DeepSeek Sparse Attention to reduce computational complexity in long-context scenarios.

  5. April 2026

    DeepSeek-V4 million-token models

    In April 2026, they coauthor DeepSeek-V4, a preview of two MoE language models that support contexts of up to one million tokens.

  6. September 2026

    DeepSeek-V4.1-Flash cache design

    In September 2026, they coauthor DeepSeek-V4.1-Flash, a multimodal MoE model with contexts of up to one million tokens. The model combines cross-layer KV-cache reuse with FP4 caching.

  7. 2022–2026

    PhD student at NUS

    They are a PhD student in the Hou Research Group at the National University of Singapore from 2022 to 2026.

Career

  1. Since 2024DeepSeekResearch coauthor

Education

  1. 2026National University of SingaporePhD

From the biography.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Yuduan Wang. 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. 16% of AI career moves in the 2020s went from a university to a companyIncludes Yuduan Wang. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  3. 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.
  4. 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.

Colleagues

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

Sources and credits

Photo: We have no published photo of Yuduan Wang yet. Send us a free-licensed photo.

  1. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model arxiv.org. Checked 21 October 2026.
  2. DeepSeek-V3 Technical Report arxiv.org. Checked 21 October 2026.
  3. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning arxiv.org. Checked 21 October 2026.
  4. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models arxiv.org. Checked 21 October 2026.
  5. DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence arxiv.org. Checked 21 October 2026.
  6. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression arxiv.org. Checked 21 October 2026.
  7. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression | alphaXiv alphaxiv.org. Checked 21 October 2026.
  8. People | Hou Group NUS blog.nus.edu.sg. Checked 21 October 2026.