Skip to content

Question about multi-head slot attention #3

Description

@kdwonn

Hello! First of all, thank you for the great work and code!

I have a question about multi-head slot attention, especially for the dimension where the softmax function is applied.

While reading, I saw that softmax is applied across every slot and head in your work. Can you please explain why it is not only applied across slots?

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