TIGER-AI-Lab / TIGER-AI-Lab/EditReward

Data Annotation Format Issue

Open
#28 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
160
Forks
6
PR merge metrics
No merged PRs in 30d

Description

If the model is optimized using the loss defined as the negative log-likelihood of the ground-truth preference from the paper, does this mean we only leverage the relative quality between the two edited images without using their exact numerical scores at all?

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.

Research direction

No file, test, or entry point is named. Start by reading the paper's loss definition and the repository's annotation and training materials to identify whether supervision uses only pairwise preference or also numerical scores. Done means documenting the annotation format and the role of exact scores clearly enough to resolve the question.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.