Skip to content

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility.

Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, Yi Wu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen

VenueA*ACL
Year2026
ProceedingsACL (1)

Browse the full ACL paper archive.