Cite
Notes
Only stored in your browser.
Attribution
Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
arXiv 2026
from 1 papers
Dapeng Wu
Hao Gu
Hao Wang
Kaixiong Gong
Sirui Han
Xiangyu Yue
Yike Guo
Yuxiao Ye