The paper investigates how the usefulness of training samples, as determined by coreset selection, depends on the learner rather than just the data. Experiments on ImageNet-100 and ImageNet-1k show that changing model width, input grid, stride, and architecture (e.g., ResNet vs. ViT) shifts the crossover point where different selection criteria (easy-first vs. geometric coverage) become optimal. These findings demonstrate that the relative value of a fixed subset of samples varies with the target learner’s capacity and structure, and that selection strategies must be tuned to the specific model they will train.
By Yangze Liu, Xiao-Long Yin, Zhongyi Han
arXiv:2605. 31244v2 Announce Type: replace Abstract: Neural scaling laws describe predictable power-law relationships between model size, dataset size, compute, and performance.
By Konstantin Nikolaou, Jonas Scheunemann, Sven Krippendorf, Samuel Tovey, Christian Holm
The paper introduces a Focal Log-Frequency Loss (f-loss) to counteract the spectral imbalance in pixel-space flow matching, where low frequencies dominate training. By balancing learning signals across frequencies and combining early frequency-domain supervision with later pixel-space refinement, the method accelerates convergence by up to 40% and improves FID and perceptual fidelity across multiple model scales. It requires no architectural changes and can replace existing flow matching losses as a drop‑in solution.
By Lucas Degeorge, Paul Couairon, Arijit Ghosh, Alexei A. Efros, David Picard, Vicky Kalogeiton
The paper introduces Multiscale Spectral Rate‑Distortion (MS‑SRD), a training‑free method that predicts the required bottleneck channel width for convolutional autoencoders at user‑specified spatial cuts, using only training images and a normalized mean‑squared error bound. MS‑SRD’s covariance‑tail rule is exact for shared linear block‑convolutional autoencoders under squared error, and a nested‑scale dominance result allows reporting an activation‑parameter Pareto frontier alongside the minimal‑latent candidate. Across thirteen grayscale datasets, the method achieves a 0.84% mean absolute percentage error in latent‑size prediction, with most predictions exact or within one channel, and demonstrates comparable performance to retrospective external widths in deployable comparisons without any training of a selector.
By Guannan Guo
arXiv:2606. 00677v1 Announce Type: new Abstract: Fourier Neural Operators are often assumed to generalize across spatial resolutions, enabling training on a coarse grid and deployment on a finer grid.
By Alex Colagrande, Paul Caillon, Eva Feillet, Alexandre Allauzen
arXiv:2610.07419v1 Announce Type: new
Abstract: Implicit neural representations (INRs) are shaped by the spectral structure induced by their input encodings and activation functions. Existing methods...
By Tamir Shor, Or Litany, Alex Bronstein
arXiv:2608.29167v1 Announce Type: new
Abstract: Robustness of segmentation models is commonly assessed through input-domain perturbations, while dependence on frequency content within learned feature...
By Subhash Kashyap
arXiv:2609.39926v1 Announce Type: new
Abstract: Achieving cross-sensor generalization and arbitrary-scale reconstruction with a single model remains challenging in hyperspectral super-resolution (HSR...
By Ji-Xuan He, Guohang Zhuang, Bo Junge, Tingyi Li, Lingchen, Miaomiao Cai, Yanan Qiao, Xiujin Liu, Junfeng Fang
The paper introduces the Meta Convolution Layer (MCL), a dynamic convolution approach that models kernels as input‑conditioned high‑order polynomial functions instead of linear mixtures of basis kernels. MCL generates a single adaptive kernel through a structured polynomial meta‑network, improving training stability and expressivity. Experiments show significant accuracy gains on ImageNet, CIFAR, and fine‑grained classification tasks when MCL is added to ResNet, Wide‑ResNet, Swin, and ViT backbones.
By Naim Reza, Md Al Amin, Ho Yub Jung
arXiv:2606. 23825v1 Announce Type: cross Abstract: Efficient small object detection is bottlenecked by the inherent feature scarcity of tiny targets, which is further aggravated by operations of spatial-domain detectors that indiscriminately discard critical high-frequency details.
By Yuhan Rui, Shihan Qiao, Yibin Lou, Mingxi Yu, Yutong Wan, Yanqiao Chen, Dongsheng Hou, Zhen Cao, Athena Zhuoming Zhong, Qi Hao
The paper introduces the Drift Contract, a spectral update geometry for local learning that improves depth robustness and hyperparameter stability. By applying momentum orthogonalization with spectral step scaling to per‑layer updates, the authors achieve consistent performance across a wide range of widths and depths on CIFAR‑10 MLPs, outperforming local Adam and providing a per‑layer, input‑conditioned drift bound. The study also shows that the spectral geometry itself, rather than step‑size rules, drives the observed depth robustness, while a negative result indicates that the stability benefit is limited to non‑normalized layers.
By Fabien Polly
The paper introduces SparK-SAR, a sparse convolutional masked pretraining framework that leverages ConvNeXt for high‑resolution Sentinel‑1 GRD SAR data. It presents three key contributions: a domain‑adapted ConvNeXt‑RS encoder with a reduced stem stride, a lightweight ConvNeXt‑512 decoder that cuts VRAM usage while matching UNet accuracy, and an analysis of FP16 instability and layer‑wise learning‑rate decay benefits. Experiments on four Copernicus‑Bench S1GRD tasks show that the 27.8 M‑parameter ConvNeXt‑RS encoder outperforms a larger ViT baseline on most tasks and demonstrates strong data efficiency, with classification saturating at 10–25 % of the SSL4EO‑S12 corpus.
By Yuki Natsume, Sang-Ho Yun, Chai Kiat Yeo