Ding, Zixiang, Guoqing Jiang, Shuai Zhang, Lin Guo, and Wei Lin. 2024. “How to Trade Off the Quantity and Capacity of Teacher Ensemble: Learning Categorical Distribution to Stochastically Employ a Teacher for Distillation”. Proceedings of the AAAI Conference on Artificial Intelligence 38 (16):17915-23. https://doi.org/10.1609/aaai.v38i16.29746.