EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
Paper
• 2511.15248 • Published
• 7 •
2
Kai Yang
yangkaiSIGS
AI & ML interests
None yet
Recent Activity
authored
a paper
8 days ago
Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation Organizations
commented a paper 4 months ago