Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration

@article{zili2026,
  title = {Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration},
  author = {Wang, Zili and Chai, Jiajun and Chen, Lin and Wang, Xiaohan and Xiang, Shiming and Yin, Guojun},
  journal = {Findings of the Association for Computational Linguistics: EMNLP 2026},
  year = {2026},
  month = {Jan},
  doi = {10.18653/2026.findings-emnlp.671},
  url = {https://doi.org/10.18653/2026.findings-emnlp.671},
}

Wang, Zili et al. (2026). Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration. Findings of the Association for Computational Linguistics: EMNLP 2026. https://doi.org/10.18653/2026.findings-emnlp.671

Wang, Zili, et al.. "Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration." Findings of the Association for Computational Linguistics: EMNLP 2026, 2026, https://doi.org/10.18653/2026.findings-emnlp.671.

Wang, Zili, et al.. "Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration." Findings of the Association for Computational Linguistics: EMNLP 2026 (2026). https://doi.org/10.18653/2026.findings-emnlp.671

Wang, Zili et al., 2026. Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration. Findings of the Association for Computational Linguistics: EMNLP 2026. Available at: <https://doi.org/10.18653/2026.findings-emnlp.671>.

TY  - JOUR
TI  - Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration
AU  - Wang, Zili
AU  - Chai, Jiajun
AU  - Chen, Lin
AU  - Wang, Xiaohan
AU  - Xiang, Shiming
AU  - Yin, Guojun
PY  - 2026
JO  - Findings of the Association for Computational Linguistics: EMNLP 2026
DO  - 10.18653/2026.findings-emnlp.671
UR  - https://doi.org/10.18653/2026.findings-emnlp.671
ER  -