ld-ing/qdhf

Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization (ICML 2024)

27
/ 100
Experimental

This project helps improve the creativity and variety of outputs from AI models, particularly in generating images or robot behaviors. It takes human judgments about the similarity of different AI-generated items and uses that feedback to help the AI produce a broader range of high-quality results. This is useful for researchers and practitioners working with generative AI or evolutionary robotics who want more diverse and novel solutions.

No commits in the last 6 months.

Use this if you need an AI to explore a wider array of creative solutions or behaviors rather than repeatedly generating similar optimal outcomes.

Not ideal if your primary goal is to find a single, best-performing solution without concern for diversity or novelty.

Generative AI Robotics Creative Design AI Model Training Open-Ended Generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

19

Forks

1

Language

Python

License

MIT

Last pushed

Apr 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/ld-ing/qdhf"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.