May 6, 2025SWALP: Stochastic Weight Averaging in Low-Precision TrainingSWALP, 通过 SWA 稳定低精度训练NoteLow-PrecisionFQTSWAEmpiricalICML2019
April 1, 2025A Self-Attentive Model for Knowledge TracingSAKT, 自注意力知识追踪NoteKnowledge TracingAttentionEmpiricalEDM2019