PeopleofSuperintelligence

Researcher

Oliver Wang

Oliver Wang is a research scientist who builds image and video generation models at Google DeepMind. He studied computer science at Cornell and UC Santa Cruz, worked at Disney Research Zürich from 2009 to 2015, and then spent 2015 to 2023 at Adobe Research in Seattle, where he shipped tools such as Content Aware Fill for Video and founded and co-led Firefly through its initial release. In 2018 he coauthored a paper showing that deep network features outperform earlier metrics at matching human judgments of perceptual similarity. After joining Google DeepMind in 2023, he became tech lead for Gemini 2.5 Flash Image, the Nano Banana model, and in 2025 he discussed how it was built on the TWIML AI and a16z podcasts. He is a principal scientist at Google DeepMind in Seattle and leads the Nano Banana team.

Badges

Timeline

  1. 1999–2010

    A PhD at UC Santa Cruz

    From 1999 to 2003 he studies computer science at Cornell University for a BA. At UC Santa Cruz he works toward an MS from 2004 to 2006 and a PhD in computer science from 2006 to 2010.

  2. 2009–2015

    Researcher at Disney Research Zürich

    Disney Research Zürich employs him as a postdoc and research scientist from 2009 to 2015. In 2014 he is first author of VideoSnapping, a SIGGRAPH paper on interactive synchronization of multiple videos; in 2015 he coauthors Phase-Based Frame Interpolation for Video, a CVPR oral.

  3. 2015–2023

    Research scientist at Adobe

    Adobe Research in Seattle employs him from 2015 to 2023 as research scientist, senior research scientist and principal scientist. Products he ships there include Camera-Shake Deblur in After Effects CC 2017.2, Video Loops in Adobe Stock in 2018 and Content Aware Fill for Video in After Effects CC 2019.

  4. 2018

    Deep features as a perceptual metric

    In 2018 he coauthors "The Unreasonable Effectiveness of Deep Features as a Perceptual Metric" with Richard Zhang, Phillip Isola, Alexei A. Efros and Eli Shechtman, accepted to CVPR 2018. The paper introduces a dataset of human perceptual similarity judgments and finds that deep features outperform all previous metrics by large margins on it.

  5. 2023

    Founding Adobe Firefly

    At Adobe he founds and co-leads Firefly from its conception until its initial release. Firefly reaches Express and Photoshop in 2023.

  6. 2023–2024

    Joining Google DeepMind

    In 2023 he joins Google DeepMind in Seattle to work on GenAI, developing image and video generation models. Products he ships there include Gemini and Imagen 2 in 2023, then Imagen 3, Veo 2 and Gemini 2.0 native image output in 2024.

  7. 2025

    Tech lead for Nano Banana

    He is tech lead for Gemini 2.5 Flash Image, better known as Nano Banana, a model that generates and iteratively edits images while maintaining consistency. In September 2025 he discusses the newly released model on the TWIML AI podcast, and in October 2025 he discusses how it was created on the a16z podcast. Nano Banana Pro, listed as Gemini 3.0 Pro Image, is among his shipped products in 2025.

  8. As of October 2026

    Leading the Nano Banana team

    He is a principal scientist at Google DeepMind in Seattle, with a research focus on multimodal AI, and leads the Nano Banana team. His shipped products for 2026 include Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) and Gemini Omni Flash.

Career

  1. Since 2023Google DeepMindPrincipal Scientist
  2. 2015–2023AdobeResearch Scientist, Senior Research Scientist, and Principal Scientist
  3. 2009–2015The Walt Disney CompanyPostdoc and Research Scientist

Education

  1. 2010University of California, Santa CruzPhD
  2. 2006University of California, Santa CruzMS
  3. 2003Cornell UniversityBA

From the biography.

Videos

YouTube videos in which Oliver Wang speaks or appears, newest first. A model chose them from YouTube search results. List updated 22 October 2026.

  1. Inside Nano Banana 🍌 and the Future of Vision-Language Models [Oliver Wang] - 748The TWIML AI Podcast with Sam Charrington · 23 September 2025 · 1 h 3 min

Video data from YouTube API Services. By watching you agree to the YouTube Terms of Service. How we use YouTube data.

  1. Google had the most people shaping AI every year from 2014 to 2025Includes Google. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  2. Google has the highest combined h-index among AI organizationsIncludes Google. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  3. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Google. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  4. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Google. 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.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

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

  1. Oliver Wang - Personal Homepage oliverwang.info. Checked 22 October 2026.
  2. [1801.03924] The Unreasonable Effectiveness of Deep Features as a Perceptual Metric arxiv.org. Checked 22 October 2026.
  3. Oliver Wang | TWIML - The Voice of Machine Learning & AI twimlai.com. Checked 22 October 2026.
  4. Inside Nano Banana and the Future of Vision-Language Models | TWIML - The Voice of Machine Learning & AI twimlai.com. Checked 22 October 2026.
  5. Google DeepMind Developers: How Nano Banana Was Made | Andreessen Horowitz a16z.com. Checked 22 October 2026.