1.Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
Cheng, Jie, Xiong, G More...
Advances in Neural Information Processing Systems[1049-5258], Published 2025, Volume 38, Pages 145854-145879
收錄情况: SCOPUS
本系統需要使用 Internet Explorer 9.0 以上Firefox || Chrome瀏覽器
Copyright © 2018 澳門科技大學學者庫