PeopleofSuperintelligence

Researcher

Hartwig Adam

Hartwig Adam is a Google researcher whose work covers efficient vision models for mobile devices and image segmentation. He is a senior director of research at Google DeepMind. Before joining Google in 2006, he worked at the University of Southern California's vision laboratory and at Eyematic Interfaces and Neven Vision. At Google he co-authored MobileNets in 2017 and two DeepLab segmentation papers in 2017 and 2018. He also co-authored VideoPoet, a language model for zero-shot video generation that received a Best Paper award at ICML 2024.

Works
76
Citations
57,308
h-index
35

Publication numbers from OpenAlex, as of 15 October 2026.

Timeline

  1. 1998–1999

    Vision research at USC

    He works as a research scientist in the Laboratory for Biological and Computational Vision at the University of Southern California in 1998.

  2. 1999–2006

    Engineering at Eyematic and Neven Vision

    He joins Eyematic Interfaces as a senior software engineer in 1999 and becomes vice president of platform technology at Neven Vision in 2004.

  3. 2006–2024

    Engineering director at Google

    He joins Google as an engineering director in 2006, where he leads a group that develops computer vision and machine perception systems for mobile devices.

  4. 2017

    MobileNets for mobile vision

    He helps build MobileNets, a class of efficient models for mobile and embedded vision, which Google publishes in 2017.

  5. 2017–2018

    DeepLab segmentation papers

    He co-authors Rethinking Atrous Convolution for Semantic Image Segmentation in 2017 and Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation in 2018.

  6. December 2023

    Co-authoring VideoPoet

    He co-authors VideoPoet, a large language model for zero-shot video generation, which appears on arXiv in December 2023.

  7. 2024

    A Best Paper at ICML

    VideoPoet, which he co-authored, wins a Best Paper award at ICML 2024.

  8. Since 2024

    Senior director at DeepMind

    He is a senior director of research at Google DeepMind, working across computer vision, machine learning, and machine perception.

Sources and credits

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

  1. Hartwig Adam | alphaXiv alphaxiv.org. Checked 15 October 2026.
  2. MobileNets: Open-Source Models for Efficient On-Device Vision research.google. Checked 15 October 2026.
  3. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications arxiv.org. Checked 15 October 2026.
  4. Rethinking Atrous Convolution for Semantic Image Segmentation arxiv.org. Checked 15 October 2026.
  5. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation arxiv.org. Checked 15 October 2026.
  6. VideoPoet: A Large Language Model for Zero-Shot Video Generation arxiv.org. Checked 15 October 2026.
  7. Hartwig Adam research.google. Checked 15 October 2026.
  8. Award-winning paper in ICML 2024 on “VideoPoet: A large language model for zero-shot video generation.” | Irfan Essa irfanessa.gatech.edu. Checked 15 October 2026.
  9. ICML Oral VideoPoet: A Large Language Model for Zero-Shot Video Generation icml.cc. Checked 15 October 2026.