PeopleofSuperintelligence

Researcher

Yixuan Wei

Also known as 韦毅轩, Eason Wei

Yixuan Wei co-wrote computer-vision papers on Swin Transformer models and language-image pretraining, as well as an alignment paper for large language models. They studied automation at Tsinghua University from September 2016. In 2019 they co-wrote DeepHuman, a framework for 3D human reconstruction from a single RGB image. Swin Transformer, which they co-wrote, received the ICCV 2021 Best Paper award, known as the Marr Prize. Swin Transformer V2 and Video Swin Transformer followed as CVPR 2022 papers, iCLIP appeared at CVPR 2023, and Xwin-LM was published in May 2024.

Works
73
Citations
40,390
h-index
23

Publication numbers from OpenAlex, as of 15 October 2026.

Timeline

  1. September 2016

    Automation studies at Tsinghua

    They study automation at Tsinghua University from September 2016.

  2. 2019

    The DeepHuman framework

    They co-write DeepHuman in 2019, a framework for 3D human reconstruction from a single RGB image.

  3. 2021

    Swin Transformer and the Marr Prize

    They co-write Swin Transformer, which wins the ICCV 2021 Best Paper award, known as the Marr Prize.

  4. 2022

    Swin Transformer V2 at CVPR

    They co-write Swin Transformer V2: Scaling Up Capacity and Resolution, a CVPR 2022 paper.

  5. 2022

    Video Swin Transformer at CVPR

    They co-write Video Swin Transformer, a CVPR 2022 paper.

  6. 2023

    iCLIP at CVPR 2023

    They co-write iCLIP, which combines image classification with contrastive language-image pre-training, at CVPR 2023.

  7. May 2024

    Xwin-LM for LLM alignment

    They co-write Xwin-LM, a paper on strong and scalable alignment practice for LLMs, published in May 2024.

Sources and credits

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

  1. Yixuan(Eason) Wei weiyx16.github.io. Checked 15 October 2026.
  2. [1903.06473] DeepHuman: 3D Human Reconstruction from a Single Image arxiv.org. Checked 15 October 2026.
  3. [2103.14030] Swin Transformer: Hierarchical Vision Transformer using Shifted Windows arxiv.org. Checked 15 October 2026.
  4. Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows - Microsoft Research microsoft.com. Checked 15 October 2026.
  5. ICCV 2021 PAPER AWARDS | ICCV 2021 iccv2021.thecvf.com. Checked 15 October 2026.
  6. CVPR 2022 Open Access Repository openaccess.thecvf.com. Checked 15 October 2026.
  7. CVPR 2022 Open Access Repository openaccess.thecvf.com. Checked 15 October 2026.
  8. CVPR 2023 Open Access Repository openaccess.thecvf.com. Checked 15 October 2026.
  9. iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-training for Visual Recognition - Microsoft Research microsoft.com. Checked 15 October 2026.
  10. [2405.20335] Xwin-LM: Strong and Scalable Alignment Practice for LLMs arxiv.org. Checked 15 October 2026.
  11. Paper page - Xwin-LM: Strong and Scalable Alignment Practice for LLMs huggingface.co. Checked 15 October 2026.