PeopleofSuperintelligence

Builder

Patrick von Platen

Patrick von Platen is a research engineer behind open-source AI libraries and models, from Hugging Face's Diffusers to the reasoning model Magistral. A University of Cambridge PhD, he co-authored the 2020 Transformers library paper and by 2022 was the core developer of the Diffusers library at Hugging Face. His papers include XLS-R, a speech model trained on 128 languages in 2021, and BLOOM, a 176B-parameter open-access language model, in 2022. In 2025, he co-authored Magistral, Mistral's first reasoning model, and the audio chat models Voxtral. He is a research engineer at Mistral AI, where he contributes to vLLM.

Works
25
Links
GitHub

Publication numbers from OpenAlex, as of 22 October 2026. Citations and h-index are hidden because this OpenAlex record may be incomplete or mix in other authors.

Timeline

  1. 2020

    The Transformers library paper

    In 2020, he is among the authors of "Transformers: State-of-the-Art Natural Language Processing", the EMNLP system-demonstration paper on Transformers. The open-source library offers Transformer architectures under a unified API, backed by a collection of pretrained models made by and available for the community.

  2. 2021

    Wav2Vec2 and XLS-R

    He publishes the Hugging Face guide "Fine-Tune Wav2Vec2 for English ASR with Transformers" in March 2021. In November 2021, he is among the authors of XLS-R, a wav2vec 2.0-based model with up to 2B parameters trained on nearly half a million hours of public speech audio in 128 languages.

  3. 2022

    Core developer of Diffusers

    In August 2022, he is among the authors of the Hugging Face blog post "Stable Diffusion with Diffusers", with Suraj Patil, Pedro Cuenca and Nathan Lambert. By November 2022, he is a research engineer at Hugging Face and the core developer of its diffusers library, and he holds a PhD from the University of Cambridge.

  4. November 2022

    The BLOOM language model

    In November 2022, he is among the BigScience Workshop authors of BLOOM, a 176B-parameter open-access multilingual language model. BLOOM is a decoder-only Transformer trained on the ROOTS corpus, which covers 46 natural and 13 programming languages.

  5. October 2024

    Pixtral 12B

    In October 2024, he is among the authors of Pixtral 12B, a 12-billion-parameter multimodal language model. Its new vision encoder, trained from scratch, takes in images at their natural resolution and aspect ratio.

  6. June–July 2025

    Magistral and Voxtral

    In June 2025, he is among the authors of Magistral, Mistral's first reasoning model, which comes with Mistral's own scalable reinforcement learning pipeline; Magistral Small is open-sourced under Apache 2.0. In July 2025, he is among the authors of Voxtral Mini and Voxtral Small, two multimodal audio chat models released under Apache 2.0.

  7. January 2026

    The Ministral 3 models

    In January 2026, he is among the authors of Ministral 3, a family of dense language models in 3B, 8B and 14B parameters. Each size comes as a base, an instruction-finetuned and a reasoning model under Apache 2.0, derived through Cascade Distillation.

  8. As of October 2026

    Research engineer at Mistral AI

    He is a research engineer at Mistral AI, focused on natural language processing and scalable AI systems, and contributes to vLLM. A former core maintainer of Transformers who created Diffusers, he gives the keynote "Stream Everything - Moving from Request input to Streaming input" at PyTorch Conference Europe in April 2026.

Career

  1. NowMistral AIResearch Engineer
  2. Hugging FaceResearch Engineer and core developer of Diffusers

Education

  1. University of CambridgePhD

From the biography.

  1. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Patrick von Platen. 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.
  2. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Mistral AI. 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.
  3. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Mistral AI. 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. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Mistral AI. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.

Sources and credits

Photo: We have no published photo of Patrick von Platen yet. Send us a free-licensed photo.

  1. Transformers: State-of-the-Art Natural Language Processing - ACL Anthology aclanthology.org. Checked 20 October 2026.
  2. Fine-Tune Wav2Vec2 for English ASR in Hugging Face with Transformers huggingface.co. Checked 20 October 2026.
  3. XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale arxiv.org. Checked 20 October 2026.
  4. Stable Diffusion with Diffusers huggingface.co. Checked 20 October 2026.
  5. Colloquium: Generating Images and Audio With the Hugging Face Diffusers Library crossmodal-learning.org. Checked 20 October 2026.
  6. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model arxiv.org. Checked 20 October 2026.
  7. Pixtral 12B arxiv.org. Checked 20 October 2026.
  8. Magistral arxiv.org. Checked 20 October 2026.
  9. Voxtral arxiv.org. Checked 20 October 2026.
  10. Ministral 3 arxiv.org. Checked 20 October 2026.
  11. Keynote: Stream Everything - Moving from Request input to Streaming input - Patrick von Platen, Research Engineer, Mistral AI pytorchconferenceeu2026.sched.com. Checked 20 October 2026.