Skip to content

Introduction

Established in 2023, the ByteDance Seed team is dedicated to discovering new approaches to general intelligence and pushing the boundaries of AI. Our research spans large language models, speech, vision, world models, AI infrastructure, next-generation interfaces and more. With a long-term vision and determination in AI, the ByteDance Seed team remains committed to foundational research. We aim to become a world-class AI research team that drives real technological progress and delivers societal benefits. With labs across China, Singapore, and the U.S., our team has already released industry-leading general-purpose large models and advanced multimodal capabilities, powering over 50 real-world applications — including Doubao, Coze, and Jimeng.

Website

ByteDance Seed

Contact Us

email: doubao-llm@bytedance.com

Popular repositories Loading

  1. Bagel Bagel Public

    Open-source unified multimodal model

    Python 5.6k 491

  2. Depth-Anything-3 Depth-Anything-3 Public

    Depth Anything 3

    Python 4.1k 370

  3. VeOmni VeOmni Public

    VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

    Python 1.6k 133

  4. Seed1.5-VL Seed1.5-VL Public

    Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

    Jupyter Notebook 1.5k 60

  5. Triton-distributed Triton-distributed Public

    Distributed Compiler based on Triton for Parallel Systems

    Python 1.3k 116

  6. m3-agent m3-agent Public

    Python 1.2k 100

Repositories

Showing 10 of 50 repositories
  • ByteDance-Seed/Stable-DiffCoder’s past year of commit activity
    4 MIT 2 0 0 Updated Jan 22, 2026
  • VeOmni Public

    VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

    ByteDance-Seed/VeOmni’s past year of commit activity
    Python 1,565 Apache-2.0 133 44 20 Updated Jan 22, 2026
  • EvaLearn Public

    EvaLearn is a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in challenging tasks.

    ByteDance-Seed/EvaLearn’s past year of commit activity
    Python 431 Apache-2.0 12 0 0 Updated Jan 18, 2026
  • SpatialTree Public
    ByteDance-Seed/SpatialTree’s past year of commit activity
    Shell 1 0 0 0 Updated Jan 18, 2026
  • cryofm Public

    Generative foundation model for cryo-EM density maps.

    ByteDance-Seed/cryofm’s past year of commit activity
    Python 15 Apache-2.0 2 1 0 Updated Jan 15, 2026
  • byteff2 Public
    ByteDance-Seed/byteff2’s past year of commit activity
    Python 29 Apache-2.0 3 0 0 Updated Jan 14, 2026
  • AInsteinBench Public
    ByteDance-Seed/AInsteinBench’s past year of commit activity
    Python 3 Apache-2.0 0 0 0 Updated Jan 7, 2026
  • bamboo_mixer Public
    ByteDance-Seed/bamboo_mixer’s past year of commit activity
    Python 29 Apache-2.0 4 0 0 Updated Jan 5, 2026
  • DAComp Public

    DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle

    ByteDance-Seed/DAComp’s past year of commit activity
    Python 373 0 0 0 Updated Jan 4, 2026
  • DATAMASK Public

    Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning

    ByteDance-Seed/DATAMASK’s past year of commit activity
    Python 9 Apache-2.0 0 0 0 Updated Jan 4, 2026

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

Loading…