Skip navigation
Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal…
0:00 / 1:20

Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal…

Ceyuan Yang

@CeyuanY2.2K followers

Visit on X
224 likesDownloadOriginal post

32,971 views

Introducing Omni, one unified model can support any-to-any multimodal modeling, including multimodal understanding, image/video generation and editing, world modeling and 3D reconstruction. All in one that adopts standard mixture-of-experts arch with only 3B activations.

9 Comments

Comments from the original post on X (Twitter)

  • Ceyuan Yang's profile picture

    @CeyuanY

    Any-to-any training enables multimodal context unrolling where the model explicitly reasons across multiple modal representations before producing predictions. This reframes “unification” as a mechanism that scales context—not only in length, but in structure and utility for downstream decisions.

    8 likes

  • Ceyuan Yang's profile picture

    @CeyuanY

    Started last summer, but shared much later and less detailed than we hoped. It was built by a small team under many constraints, with plenty of imperfections, but also with a lot of support from people who truely believed in it. It only made us believe more: the future is multimodal.

    8 likes

  • Ceyuan Yang's profile picture

    @CeyuanY

    Homepage: ArXiv:

    10 likes

  • Kangfu Mei's profile picture

    @KangfuM

    Congratulations Ceyuan! That’s great work!

    2 likes

  • Jiazhi Yang's profile picture

    @jiazhi_yang2024

    Congrats Ceyuan!

    2 likes

  • P.MOHANSRINIVAS's profile picture

    @PMOHANSRINIVAS1

    Any GitHub repo link @CeyuanY for testing results

  • Leo@Yuhao's profile picture

    @LeoLau_yuhao

    Congrats

  • Astrid Wilde 🌞's profile picture

    @astridwilde

    interesting

  • Kairun Wen's profile picture

    @KairunWen

    Congrats🥳!