PeopleofSuperintelligence

Researcher

Lucas Beyer

Lucas Beyer is a computer-vision researcher whose work helped apply Transformers to image recognition and connect image and language. He grew up in Belgium interested in video-game AI, studied computational engineering at RWTH Aachen, and completed a doctorate in computer vision for mobile robots. At Google Brain and Google DeepMind, he co-led multimodal research and co-authored Vision Transformer, PaLI, SigLIP, and PaliGemma. He helped start OpenAI’s Zürich office in 2024, joined Meta in 2025, and now researches multimodal AI in Zürich.

Now at
Meta
Works
57

Publication numbers from OpenAlex, as of 15 October 2026. Citations and h-index are hidden because this OpenAlex record may be incomplete or mix in other authors.

Timeline

  1. 2006–2012

    Computational engineering studies

    After growing up in Belgium interested in video-game AI, he studies Computational Engineering Science at RWTH Aachen and completes a diploma thesis on graphics adapters for computational biology in 2012.

  2. 2013–2018

    A computer vision doctorate

    At RWTH Aachen, he researches deep learning for computer vision on mobile robots and completes his PhD in 2018.

  3. 2018–2024

    Co-leading multimodal research

    He joins Google Brain in Zürich in 2018 and co-leads multimodal research at Google Brain and Google DeepMind from 2021 to 2024. He co-authors Vision Transformer in 2021, PaLI in 2022, SigLIP in 2023, and PaliGemma in 2024, advancing image recognition and vision-language systems.

  4. December 2024

    Starting OpenAI’s Zürich office

    In December 2024, he joins OpenAI from Google DeepMind with Alexander Kolesnikov and Xiaohua Zhai, helping establish its Zürich office for multimodal AI work.

  5. Since 2025

    Multimodal research at Meta

    In June 2025, he moves from OpenAI’s Zürich office to Meta. At a June 2026 Transformers talk, he is working at Meta and continues multimodal AI research in Zürich.

Sources and credits

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

  1. Lucas Beyer’s home lucasb.eyer.be. Checked 14 October 2026.
  2. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale arxiv.org. Checked 14 October 2026.
  3. PaLI: A Jointly-Scaled Multilingual Language-Image Model arxiv.org. Checked 14 October 2026.
  4. Sigmoid Loss for Language Image Pre-Training arxiv.org. Checked 14 October 2026.
  5. PaliGemma: A versatile 3B VLM for transfer arxiv.org. Checked 14 October 2026.
  6. OpenAI Poaches 3 Top Engineers From DeepMind | WIRED wired.com. Checked 14 October 2026.
  7. Ex-OpenAI researcher confirms move to Meta, denies $100 million payout | The Economic Times economictimes.indiatimes.com. Checked 14 October 2026.
  8. Lucas Beyer on Transformers: A Talk at the Zurich AI Academy | David Wright davidwright.ch. Checked 14 October 2026.