Skip to content

flow matching time steps #35

@coga-kj

Description

@coga-kj

When training flow matching, it seems like the model predicts the noise all at once without using time steps, but during inference, it uses 10 time steps. Is this approach used because training with a harder problem and performing inference with an easier noise prediction leads to better performance?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions