Shu, Y., Wei, C., Lin, H., Qiu, S., & Xiong, H. (2026). Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent.
Citazione stile Chigago Style (17a edizione)Shu, Yao, Chenxing Wei, Hongbin Lin, Shuang Qiu, e Hui Xiong. Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent. 2026.
Citatione MLA (9a ed.)Shu, Yao, et al. Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent. 2026.
Attenzione: Queste citazioni potrebbero non essere precise al 100%.