Skip to content

A collection of strong multimodal models for building multimodal AGI agents

License

Notifications You must be signed in to change notification settings

om-ai-lab/OmModel

Repository files navigation

speed OmModel

English | 中文

A collection of strong multimodal models for building the best multimodal agents


🗓️ Updates

  • 07/04/2024: OmAgent is now open-sourced. 🌟 Dive into our Multi-modal Agent Framework for complex video understanding. Read more in our paper.
  • 06/09/2024: OmChat has been released. 🎉 Discover the capabilities of our multimodal language models, featuring robust video understanding and support for context up to 512k. More details in the technical report.
  • 03/12/2024: OmDet is now open-sourced. 🚀 Experience our fast and accurate Open Vocabulary Detection (OVD) model, achieving 100 FPS. Learn more in our paper.

🗃️ Projects

Here are the various projects we've worked on at OmLab:

⭐️ OmAgent

Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer

speed

⭐️ OmDet

Fast and accurate open-vocabulary end-to-end object detection

Image 1

⭐️ OmChat

Multimodal Language Models with Strong Long Context and Video Understanding

speed

⭐️ OVDEval

A Comprehensive Evaluation Benchmark for Open-Vocabulary Detection

speed


📜 Papers

Here are the research papers published by OmLab:

Published in: AAAI, 2024

Published in: IET Computer Vision, 2024

Published in: Arxiv. 2024

Published in: Arxiv. 2024

Published in: Arxiv. 2024

Published in: NAACL, 2021


📬 Contact

For more information, feel free to reach out to us at [email protected].


Thank you for visiting OmModel's repository. We hope you find our projects and papers insightful and useful!

About

A collection of strong multimodal models for building multimodal AGI agents

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published