Wei, K., & Huang, R. (2026). MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting.
Style de citation Chicago (17e éd.)Wei, Kangda, et Ruihong Huang. MMR-GRPO: Accelerating GRPO-Style Training Through Diversity-Aware Reward Reweighting. 2026.
Style de citation MLA (9e éd.)Wei, Kangda, et Ruihong Huang. MMR-GRPO: Accelerating GRPO-Style Training Through Diversity-Aware Reward Reweighting. 2026.
Attention : ces citations peuvent ne pas être correctes à 100%.