arXiv:2606. 00344v1 Announce Type: new Abstract: Neural collapse is a structural property of the last-hidden-layer activations in neural network classification models, when trained beyond a zero classification error.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2608. 09417v2 Announce Type: replace Abstract: Deep decoder-only Transformers often replace the original Post-Norm architecture with Pre-Norm variants because Post-Norm training is highly sensitive to warmup and learning rate under conventional initialization schemes.
arXiv:2608. 09417v1 Announce Type: new Abstract: Deep decoder-only Transformers often replace the original Post-Norm architecture with Pre-Norm variants because Post-Norm training is highly sensitive to warmup and learning rate under conventional initialization schemes.
arXiv:2606. 11319v1 Announce Type: new Abstract: Learning from imperfect data is a central theme in machine learning, connecting practical questions of robustness to fundamental questions of learnability.
arXiv:2607. 12094v1 Announce Type: cross Abstract: Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models.
arXiv:2508. 09697v4 Announce Type: replace Abstract: Noisy labels are inevitable in real-world multimedia applications.
arXiv:2511. 01938v3 Announce Type: replace-cross Abstract: Grokking is a puzzling phenomenon in neural networks where full generalization occurs only after a substantial delay following the complete memorization of the training data.