Liu, S., He, Z., Zhan, G., Tao, L., Zheng, Z., Wu, J., . . . Li, S. E. (2026). STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens.
Style de citation Chicago (17e éd.)Liu, Shiqi, et al. STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens. 2026.
Style de citation MLA (9e éd.)Liu, Shiqi, et al. STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens. 2026.
Attention : ces citations peuvent ne pas être correctes à 100%.