The paper introduces the Frequency Selective Neural Network (FSNN), a new foundation architecture for time‑series learning that embeds advanced signal‑processing mathematics into its neural topology. By using a fully differentiable Wiener‑like filter bank optimized with complex‑domain backpropagation, FSNN autonomously discovers and isolates the precise physical modes of a given task, thereby avoiding the spectral entanglement that plagues CNNs, RNNs, and Transformers. Extensive evaluations show that FSNN achieves state‑of‑the‑art predictive performance, attaining 77.0 % average accuracy on the 10 multivariate UEA datasets and leading all major metrics on the imbalanced PTB‑XL ECG benchmark, while converging directly on physically meaningful frequency bands such as the cardiac QRS complex.
By Hui Huang, Ye Sun, Shiyan Hu
arXiv:2607.05176v3 Announce Type: replace
Abstract: Small object detection (SOD) remains a challenging task in real-world applications. Despite recent advances, existing detectors remain limited by r...
By Aiwen Liu, Chengguang Zhu, Gang Wang, Dandan Zhu, Haodong Lin, Yan Wang, Huiyu Zhou, Zhengyi Pan
arXiv:2609.22139v1 Announce Type: cross
Abstract: Automatic modulation classification (AMC) of received radio signals is prudent for further signal processing tasks such as communication monitoring,...
By Qamar Ijaz, Nayyer Aafaq
The paper introduces CAFE+FNO, a Fourier Neural Operator variant that enhances kernel generation by combining Fourier–Chebyshev features through parallel affine branches and a Hadamard product. This method produces frequency interactions explicitly, allowing a kernel MLP to map each normalized spectral coordinate to a complex channel‑mixing matrix while keeping the number of trainable parameters independent of the number of modes. Experiments on five PDE benchmarks and ablation studies demonstrate the effectiveness of the proposed basis configuration, multiplicative composition, and bandwidth learnability.
By Hyungjoon Juen, Minwoo Shin
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:2604. 07421v3 Announce Type: replace Abstract: Full-waveform inversion (FWI) is pivotal for reconstructing high-resolution subsurface velocity models but remains computationally intensive and ill-posed.
By Zhenyu Wang, Peiyuan Li, Yongxiang Shi, Ruoyu Wu, Chenfei Liao, Lei Zhang
arXiv:2606. 00884v1 Announce Type: cross Abstract: We study cross-subject emotion recognition from EEG, a practically important yet challenging problem in brain-computer interfaces.
By Jiaxin Qing, Lexin Li
arXiv:2605. 29263v2 Announce Type: replace Abstract: Low-channel wearable electroencephalography (EEG) is attractive for long-term monitoring, but four frontal electrodes provide only a sparse and spatially biased view of distributed scalp activity.
By Minghao Xiao
The paper introduces PI-AMFM, a permutation‑invariant neural framework that learns to decompose biomedical signals into variable‑cardinality amplitude‑ and frequency‑modulated (AM‑FM) modes. It combines a multiscale temporal encoder, a Mamba backbone, and component‑presence estimation, using Hungarian matching during training to handle unknown numbers of components. Experiments on synthetic AM‑FM signals and photoplethysmographic recordings show that PI‑AMFM outperforms existing methods in decomposition accuracy and successfully captures cardiac and respiratory dynamics without prior knowledge of mode count.
By Youngsun Kong, Ki H. Chon
arXiv:2609.22807v1 Announce Type: new
Abstract: Implicit Neural Representation (INR) leverages neural networks to represent discrete signals such as images as continuous ones, where the network weigh...
By Jinglei Shi, Xinran Chang, Jiaqi Cui, Yingjie Xia, Zhaolin Xiao, Chongyi Li
arXiv:2607. 17441v1 Announce Type: cross Abstract: Deepfake generation has raised growing concerns regarding digital media authenticity, misinformation, identity fraud, and public trust.
By Pamela Kirui, Cho Hyuk, Qingzhong Liu, Haodi Jiang
LaST‑SR introduces a Laplace‑inspired steady‑transient complex‑frequency decomposition for single‑image super‑resolution. The method couples a global full‑spectrum Fourier branch with a window‑conditioned local complex‑frequency branch, and fuses them via a Steady‑Transient Collaborative Aggregation module. Experiments on five benchmarks demonstrate that LaST‑SR achieves the highest PSNR/SSIM for ×2 and ×4 upscaling, with ablation studies confirming the effectiveness of its architecture.
By Linhao Li, Zhaojie Pan, Langkun Chen