microsoft / microsoft/mattergen
Question about quantitative results for conditional generation
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.8k
- Forks
- 351
- Avg merge
- 1h 3m
- Merged PRs (30d)
- 4
Description
Hi, thanks for releasing the paper and code.
I noticed that the paper and repository provide detailed quantitative tables mainly for unconditional generation. For conditional generation (e.g., conditioning on target properties), the results are mostly presented via distributions or task-specific examples.
I was wondering whether you have quantitative summary tables for conditional generation, similar to the unconditional benchmarks?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the paper and repository's quantitative unconditional benchmarks alongside the conditional-generation results described in the issue. Determine whether the existing conditional evaluations support summary tables; done would mean documenting those results or clarifying their absence.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100