Cite
Notes
Only stored in your browser.
Attribution
Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints
arXiv 2025
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
from 2 papers
Bo Zhou
Chonghua Liao
Guanhua Huang
Huazhe Xu
Kejiao Li
Mingze Wang
Qi Yi
Ruibin Xiong
Siheng Li
Xue Gong