Training Language Models to Self-Correct via Reinforcement Learning
Paper
β’
2409.12917
β’
Published
β’
140
Andre Ratzenberger
cyan2k
AI & ML interests
using the tech of tomorrow to make apps for today
Recent Activity
liked
a model
22 days ago
ostris/Z-Image-De-Turbo
liked
a model
3 months ago
nunchaku-tech/nunchaku-qwen-image-edit-2509
liked
a model
3 months ago
Kwaipilot/KAT-Dev
Organizations
upvoted
a
paper
over 1 year ago