Wang, T., Li, S., Sun, Y., Ding, D., & Dobriban, E. (2026). Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR.
Style de citation Chicago (17e éd.)Wang, Tao, Shuo Li, Yan Sun, Dongsheng Ding, et Edgar Dobriban. Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR. 2026.
Style de citation MLA (9e éd.)Wang, Tao, et al. Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR. 2026.
Attention : ces citations peuvent ne pas être correctes à 100%.