[Suggestion] Acknowledging UCGM in both Code and Technical Report (as referenced in Saining Xie et al.)

Open
#36 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
45/100
Issue type
Documentation
Clarity
Mostly clear
Activity status
Stale
Tech stack
python
Domain
documentation

Research direction

Start by reviewing UniPic-3/qwen_image_edit_fast/train_cm_dmd.py lines 79-88 and compare them with the linked UCGM implementation. Then inspect the README or Technical Report reference list; the work is done when the code attribution and UCGM reference requested in the issue are added.

Written by the indexing model from the issue text.

Description

Hello @SkyworkAI-Team,

Thanks for the great work on UniPic!

While going through the code, I noticed that the implementation of the Finite Difference technique in train_cm_dmd.py shares the same logic and specific variable naming as the UCGM repository.

UniPic: train_cm_dmd.py (L79-L88)

UCGM: unigen.py (L278-L291)

Since this technique is widely recognized as originating from UCGM, other recent works (e.g., Saining Xie et al. in arXiv:2601.09881) have explicitly cited it when using the same method.

To align with these community standards, I have two kind suggestions:

  • Add a code comment: It would be helpful to mark the source in the code (e.g., # Adapted from UCGM: https://github.com/LINs-lab/UCGM) so future developers know where this technique comes from.

  • Update References: Consider adding UCGM to the reference list in the README or Technical Report to acknowledge their contribution.

Hope this is helpful for refining the project!

Dominant language
Python
Stars
875
Forks
43
PR merge metrics
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from SkyworkAI/UniPic

All issues in SkyworkAI/UniPic

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.