Cite
Notes
Only stored in your browser.
Attribution
Data-Efficient RLVR via Off-Policy Influence Guidance
arXiv 2025
from 1 papers
Aohan Zeng
Dazhi Jiang
Erle Zhu
Hongning Wang
Jiale Cheng
Jie Tang
engineer
Minlie Huang
Yilin Niu
Yuan Wang
Yuxian Gu