Su, X., Zhang, K., & Lyu, A. (2026). SFT-GRPO Data Overlap as a Post-Training Hyperparameter for Autoformalization.
Style de citation Chicago (17e éd.)Su, Xiaole, Kasey Zhang, et Andy Lyu. SFT-GRPO Data Overlap as a Post-Training Hyperparameter for Autoformalization. 2026.
Style de citation MLA (9e éd.)Su, Xiaole, et al. SFT-GRPO Data Overlap as a Post-Training Hyperparameter for Autoformalization. 2026.
Attention : ces citations peuvent ne pas être correctes à 100%.