Article
Rewarding fact fidelity with an LLM judge in GRPO: lessons from 38,000 judged rewrites
jialinyyzz
• • 2Stephen Yu PRO
jialinyyzz
AI & ML interests
Doing some fun research with ML
Recent Activity
new activity about 2 hours ago
jialinyyzz/humanizer:checkout humanizer's speculative decoding model >> 50% increase of speed new activity about 2 hours ago
jialinyyzz/humanizer:watermarking updated a Space about 13 hours ago
jialinyyzz/humanizerOrganizations
None yet
published an article 10 days ago
published an article 28 days ago
Article
We built an AI humanizer and never let it see a detector
jialinyyzz
• • 2