PeopleofSuperintelligence

Researcher

Bryan Seybold

Bryan Seybold is a machine-perception researcher at Google Research whose work spans audio classification, video understanding and multimodal generation. He coauthored studies of CNN-based audio classification, temporal action localization and video-object segmentation. With his collaborators, he developed VideoPoet, a decoder-only transformer for zero-shot video generation that won an ICML 2024 Best Paper award. In 2025, he coauthored a report on Gemini 2.5 and its reasoning, multimodality, long context and agentic capabilities.

Timeline

  1. 2017

    CNN audio classification

    In 2017, he coauthors a study comparing CNN architectures for audio classification across 70 million videos, 5.24 million hours and 30,871 labels.

  2. 2018

    TAL-Net for action localization

    In 2018, he coauthors TAL-Net, a Faster R-CNN-inspired approach to temporal action localization. Its multi-scale architecture accommodates varied action durations and extends receptive fields to capture temporal context.

  3. 2018

    Instance-embedding video segmentation

    In 2018, he coauthors an unsupervised video-object segmentation method that transfers image-trained instance embeddings and combines them with objectness and optical-flow features.

  4. 2022

    Learning from image captions

    At ECCV 2022, he coauthors a pipeline that transfers captions from image-captioning datasets to video clips and creates a weakly labeled audio-video dataset with millions of paired clips and captions.

  5. December 2023

    Introducing VideoPoet

    In December 2023, he coauthors VideoPoet, a decoder-only transformer that processes image, video, text and audio inputs for zero-shot video generation.

  6. 2024

    An ICML Best Paper

    VideoPoet receives an ICML 2024 Best Paper award. The paper presents a decoder-only transformer that generates high-quality video from multimodal inputs.

  7. 2025

    Gemini 2.5 report

    In 2025, he coauthors a report introducing Gemini 2.5 Pro and Flash and describing reasoning, multimodal understanding, long context and agentic workflows.

  8. As of October 2026

    Machine perception at Google

    As of October 2026, he works in machine perception at Google Research.

  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.

Sources and credits

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

  1. Bryan Seybold — Google Research research.google. Checked 21 October 2026.
  2. Rethinking the Faster R-CNN Architecture for Temporal Action Localization openaccess.thecvf.com. Checked 21 October 2026.
  3. Instance Embedding Transfer to Unsupervised Video Object Segmentation arxiv.org. Checked 21 October 2026.
  4. Learning Audio-Video Modalities from Image Captions ecva.net. Checked 21 October 2026.
  5. VideoPoet: A Large Language Model for Zero-Shot Video Generation arxiv.org. Checked 21 October 2026.
  6. VideoPoet: A Large Language Model for Zero-Shot Video Generation proceedings.mlr.press. Checked 21 October 2026.
  7. ICML 2024 Awards icml.cc. Checked 21 October 2026.
  8. Research — Alonso Martinez alonsorobots.com. Checked 21 October 2026.
  9. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities arxiv.org. Checked 21 October 2026.