ld-ing/qdhf
Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization (ICML 2024)
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.
Stars
19
Forks
1
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
ZiYang-xie/WorldGen
🌍 WorldGen - Generate Any 3D Scene in Seconds
aioz-ai/AIOZ-GDANCE
AIOZ-GDANCE: a large-scale dataset & baseline for music-driven group dance generation. (CVPR 2023)
worldbench/WorldLens
[CVPR 2026] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World
Kobaayyy/Awesome-CVPR2026-CVPR2025-ICCV2025-CVPR2024-ECCV2024-AIGC
A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2024 AIGC
nv-tlabs/XCube
[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies