Skip to content

questions about open-source datase #15

@hyn1426536274

Description

@hyn1426536274

Thank you for your excellent work.
I have reviewed the open-source dataset. It seems that apart from the cocktail task, most of the other cot texts are simple visual localization tasks (pick something).
I would like to know if you have only trained long-range planning or general planning skills on cocktail task(or other real machine task showcased). (Like "Scene description, Plan, What I have done, Now I need to" format)
Have you provided synthetic long-range planning data in open source datasets, as mentioned in the paper Table 11: Examples of synthetic vision-language data for long-horizon tasks.
If I missed something, I am deeply sorry. Looking forward to your reply, thank you.

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