PeopleofSuperintelligence

Researcher

Anja Hauth

Anja Hauth is affiliated with Google DeepMind, where her research covers video generation and video reasoning. She co-authored an ECCV 2022 paper, Learning Audio-Video Modalities from Image Captions. In 2023 she was data co-lead on the Gemini report, a paper on multimodal models. VideoPoet, a large language model for zero-shot video generation that she co-authored, won the ICML 2024 Best Paper Award. In 2025 she co-authored MINERVA: Evaluating Complex Video Reasoning, published at ICCV 2025.

Timeline

  1. 2022

    Learning audio-video modalities

    She is an author of Learning Audio-Video Modalities from Image Captions, an ECCV 2022 paper.

  2. 2023

    Data co-lead on Gemini

    She is data co-lead on the Gemini report, a 2023 paper on multimodal models.

  3. December 2023

    Co-authoring VideoPoet

    She co-authors VideoPoet, a large language model for zero-shot video generation. Google Research publishes a blog post on the work in December 2023.

  4. 2024

    Best Paper at ICML 2024

    The VideoPoet paper wins the ICML 2024 Best Paper Award.

  5. 2025

    MINERVA at ICCV 2025

    She co-authors MINERVA: Evaluating Complex Video Reasoning, which is published at ICCV 2025.

  6. Since 2025

    Google DeepMind affiliation

    She is affiliated with Google DeepMind on the MINERVA paper, a 2025 ICCV publication.

Sources and credits

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

  1. Learning Audio-Video Modalities from Image Captions | ML Anthology mlanthology.org. Checked 14 October 2026.
  2. Gemini: A Family of Highly Capable Multimodal Models arxiv.org. Checked 14 October 2026.
  3. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context arxiv.org. Checked 14 October 2026.
  4. VideoPoet: A large language model for zero-shot video generation research.google. Checked 14 October 2026.
  5. [2312.14125] VideoPoet: A Large Language Model for Zero-Shot Video Generation arxiv.org. Checked 14 October 2026.
  6. ICML 2024 Awards icml.cc. Checked 14 October 2026.
  7. Award-winning paper in ICML 2024 on “VideoPoet: A large language model for zero-shot video generation.” | Irfan Essa irfanessa.gatech.edu. Checked 14 October 2026.
  8. MINERVA: Evaluating Complex Video Reasoning | ML Anthology mlanthology.org. Checked 14 October 2026.
  9. Minerva: Evaluating Complex Video Reasoning arxiv.org. Checked 14 October 2026.