SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ding, Yuyang, Shi, Xinyu, Li, Juntao, Liang, Xiaobo, Tu, Zhaopeng, Zhang, Min
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!