Beyond Image Preferences - Rich Human Feedback for Text-to-Image Generation
•
13
Marian Kannwischer PRO
canwiper
AI & ML interests
RLHF & Computer Vision
Recent Activity
liked
a dataset
about 2 hours ago
Rapidata/sora-video-generation-physics-likert-scoring
liked
a dataset
about 2 hours ago
Rapidata/Runway_Frames_t2i_human_preferences
reacted
to
jasoncorkill's
post
with 🔥
3 days ago
We benchmarked @xai-org 's Aurora model, as far as we know the first public evaluation of the model at scale.
We collected 401k human annotations in over the past ~2 days for this, we have uploaded all of the annotation data here on huggingface with a fully permissive license
https://huggingface.co/datasets/Rapidata/xAI_Aurora_t2i_human_preferences
Articles
Organizations
