Request for D2-Align training code release

[Cwyxx]

Hi, thank you for your great work!

I am very interested in your paper, "Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning."

I would like to ask whether you plan to release the training code for D2-Align, i.e., Directional Decoupling Alignment. It would be very helpful for reproducing the results and further understanding the method.

Thank you!