GraphScan replaces geometric or coordinate-based scanning in Vision SSMs with learned local semantic graph routing, yielding SOTA results among such models on classification and segmentation tasks.
Efficientnet: Rethinking model scaling for convolutional neural networks
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A human-centered OOD spectrum based on perceptual difficulty shows vision-language models align best with human errors across regimes, with CNNs stronger on near-OOD and ViTs on far-OOD.
EgoWalk supplies 50 hours of real-world multimodal human navigation data in varied indoor/outdoor settings together with open pipelines that auto-generate language goal annotations and traversability masks.
A new neural network stabilizes features for rare chest X-ray diseases via momentum anchoring and multi-scale fusion on EfficientNet, achieving 0.8682 AUC on ChestX-ray14.
IMPACTX adds XAI-derived attention maps as a training constraint on standard CNNs, raising accuracy on CIFAR-10/100 and STL-10 while embedding feature attributions directly in the model.
Swish-T family adds Tanh bias to Swish activation, with Swish-T_C proposed as the main variant showing empirical gains on MNIST, CIFAR-10 and related datasets.
Supervised LDA restructuring of PCA-compressed embeddings raises silhouette separability from near zero to 0.197 in plant phenomics but yields mixed classical ML gains and persistent challenges for quantum kernel alignment under limited compute.