Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

May I ask what is the difference between v1 and v2, especially in the field of adversarial training #3

Open
MetaInsight7 opened this issue Mar 6, 2025 · 1 comment
Open

May I ask what is the difference between v1 and v2, especially in the field of adversarial training #3

MetaInsight7 opened this issue Mar 6, 2025 · 1 comment

Comments

@MetaInsight7
Copy link

May I ask what is the difference between v1 and v2, especially in the field of adversarial training
@jiequancui
Copy link
Owner

Hi, thanks for your interest in our work.

IKL loss in the v1 version of our NeurIPS paper is a special case of the GKL loss in the v2 version (the paper will be released soon).
Hyper-parameter tunning can lead to further improvement.
We will release new models as soon as possible.

Best,
Jiequan

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@MetaInsight7 @jiequancui