arXiv:2606. 30813v1 Announce Type: cross Abstract: Deep neural networks with repeated architectural blocks, such as transformers, often exhibit structured relationships across layers that emerge during training.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2606. 16112v1 Announce Type: cross Abstract: Residual architectures are ubiquitous in deep learning, but they suffer from a subtle structural limitation: the norm of the residual stream can grow rapidly with depth.
arXiv:2607. 06151v1 Announce Type: new Abstract: Generalization remains a pivotal challenge in deep learning, where traditional optimizers like Stochastic Gradient Descent (SGD) often converge to sharp minima, leading to overfitting and reduced performance on unseen data.
arXiv:2602. 07494v2 Announce Type: replace Abstract: Deeper modern architectures are costly to train, making hyperparameter transfer preferable to expensive repeated tuning.
arXiv:2605.15760v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) optimization is most commonly performed using general-purpose first-order optimizers such as Adam or SGD. Although rob...
The paper proposes a new strategy for merging layers in deep neural networks, enabling depth compression without requiring an analytical solution for convolutions with padding and without increasing kernel size. This approach addresses limitations of previous methods that struggled with padded convolutions and larger kernels, and it is validated across various architectures and datasets with measured inference speed-ups on embedded platforms.
arXiv:2106. 06998v5 Announce Type: replace Abstract: Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagation.