The paper introduces a leakage‑free, block‑based method for Neural Architecture Search (NAS) that shares runs across subjects, thereby avoiding the quadratic cost of a fully nested Leave‑One‑Subject‑Out (LOSO) evaluation. Applied to the BioVid Heat Pain dataset, the approach raises mean accuracy from 82.79 % to 83.39 % and can cut model parameters by up to 99.2 %.
Automatic pain localization, which involves identifying the anatomical origin of pain from peripheral physiological signals without patient self-report, is a clinically critical but largely unaddressed problem, particularly for non-verbal patients. This paper presents a systematic comparison of classical feature engineering and deep sequence learning for subject-independent three-class pain localization using the AI4Pain 2026 Challenge dataset, which comprises four synchronously recorded wearable modalities: electrodermal activity, blood volume pulse, respiration, and peripheral oxygen saturation recorded from 65 participants under controlled TENS-induced pain.
ONNX-Net introduces a universal representation for neural architectures using natural language descriptions, enabling instant performance prediction across diverse search spaces. The authors present ONNX-Bench, a benchmark of over 600k architecture–accuracy pairs compiled from open‑source NAS‑bench networks in ONNX format. Experiments demonstrate strong zero‑shot predictive performance with minimal pretraining, overcoming the limitations of cell‑based, graph‑encoded approaches.
arXiv:2606. 07664v1 Announce Type: cross Abstract: Neuroevolution is a representative neural architecture search paradigm that evolves both network topology and weights through evolutionary algorithms.
arXiv:2603. 19100v2 Announce Type: replace Abstract: Electroencephalography (EEG) enables non-invasive monitoring of brain activity across clinical and neurotechnology applications, yet building foundation models for EEG remains challenging due to differing electrode topologies and computational scalability, as Transformer architectures incur quadratic sequence complexity.
arXiv:2606. 23706v1 Announce Type: cross Abstract: The development of generalizable electroencephalography (EEG) decoding models is essential for robust brain-computer interfaces (BCI) and objective neural biomarkers in mental health.
The paper investigates the use of Zero Cost Proxies (ZCPs) to identify high‑performing wearable Human Activity Recognition (HAR) models without full training. Eight ZCPs were evaluated across six benchmark HAR datasets, showing that the top‑predicted architectures achieve performance within 7% of fully trained models, and training the top‑10 predictions reaches within 2% of full training. This demonstrates that ZCPs can significantly reduce computational costs while maintaining competitive accuracy in sensor‑based HAR tasks.
arXiv:2607. 11826v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) has automated the design of deep learning models but traditionally requires massive computational resources, often measured in thousands of GPU-days.
arXiv:2610.01687v1 Announce Type: cross Abstract: Test-time scaling often seeks better answers by sampling multiple responses from a frozen model, yet conventional temperature sampling generates ever...
NeuroSketch presents a practical design recipe for neural decoding, beginning with a comparative study of nine basic architectures that identifies CNN‑2D as the most effective. The recipe incorporates macro‑level gradual feature‑map expansion and early downsampling, along with micro‑level grouped convolutions, resulting in two variants—NeuroSketch‑Base (1.4M parameters) and NeuroSketch‑Large (4.2M parameters). Across nearly 5,000 experiments on eight tasks involving visual, auditory, and speech modalities and EEG, SEEG, and ECoG signals, both variants outperform ten baseline models on every task.
arXiv:2605. 17289v2 Announce Type: replace-cross Abstract: Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm.
arXiv:2606. 04063v1 Announce Type: cross Abstract: Deploying large language models (LLMs) is challenging due to their significant memory and computational requirements.