EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
Paper
•
2511.15248
•
Published
•
6
•
2
Kai Yang
yangkaiSIGS
AI & ML interests
None yet
Recent Activity
updated
a Space
25 days ago
yangkaiSIGS/entropic
authored
a paper
about 1 month ago
Thinking-Free Policy Initialization Makes Distilled Reasoning Models
More Effective and Efficient Reasoners
authored
a paper
about 1 month ago
EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
Organizations
commented
a
paper
about 1 month ago