12K参数下多种子实验揭秘：grokking现象并非普遍，而是有条件且脆弱的。
arXiv:2607.05104v1 Announce Type: cross Abstract: Grokking -- the delayed onset of generalization long after a network has fit its training set - -is …
揭示Grokking中权重范数如何通过交叉熵下的logit尺度中介作用控制延迟泛化，为理解神经网络泛化机制提供新视角。
arXiv:2606.18465v1 Announce Type: new Abstract: Grokking, the delayed jump from memorization to generalization, is usually tied to the weight norm: a …
语言模型预训练时竟出现类似“顿悟”的语法泛化延迟现象，揭示学习路径的意外转折。
arXiv:2606.00230v1 Announce Type: new Abstract: Grokking, the phenomenon in which neural networks generalize long after fitting their training data, h…
揭秘低精度训练中“弹弓损失尖峰”的成因，区分了真正“顿悟”与异常“故障”，为数值优化提供新视角。
arXiv:2605.06152v3 Announce Type: replace Abstract: Deep neural networks exhibit periodic loss spikes during unregularized long-term training, a pheno…
探索神经网络在有限维代数乘法学习中的“grokking”现象，从记忆到泛化的突然转变，拓展至更一般的代数结构。
arXiv:2602.19533v2 Announce Type: replace-cross Abstract: This paper investigates the grokking phenomenon, which refers to the sudden transition from …