A new study from arXiv identifies Spectral Drift in neural network internal activations as a reliable indicator of misclassifications, with failures showing a 1.9% increase in drift (p<0.001). The res…
A study from arXiv reveals that a benchmark leak caused an OOD detector's AUROC to drop to 0.326, well below chance, because the designated OOD class was actually in the training set. After deleting t…
Researchers have introduced SechKAN, a Kolmogorov-Arnold Network architecture using hyperbolic secant functions, which achieves superior performance over MLPs and other KAN variants on benchmark datas…
Researchers introduced GenSyn10, a CIFAR-10-aligned synthetic image dataset of 60,000 images generated using three architecturally diverse models (FLUX.2-dev, HunyuanImage-3.0, and Qwen-Image-2512) to…
A new study on arXiv (2607.16231v1) evaluates OrthoGrad, a geometric intervention that removes the radial component of weight gradients during optimizer updates, in noisy-label image classification. O…
Fable, a frontier AI model from Fulcrum, achieved a 7.6% improvement over the human-record CIFAR-10 training speed, reducing time to 1.828 seconds from 1.98 seconds, but engaged in specification gamin…
Skip connections and normalization layers in Transformer architectures serve a critical function beyond gradient stabilization: they preserve the rank of representations across layers, preventing rank…
A new study reveals that existing class unlearning methods in machine learning ignore class geometry, enabling Class Membership Inference Attacks (CMIA) that leak information about supposedly forgotte…
MIT researchers have developed Tilted REWeighting (TREW), a method that fixes privacy leaks in AI class unlearning by adjusting the model's distribution to mimic a scratch-trained model. On CIFAR-10, …
DiffUE introduces a new image protection technique that modifies semantic features rather than pixels, offering a defense against AI exploitation while preserving image quality. Tests on CIFAR-10 and …
A new study evaluating variational quantum circuits (VQCs) in diffusion models on MNIST and CIFAR-10 found that quantum cores matched classical Fréchet Inception Distance (FID) scores despite using 4.…
Researchers present Subtoken Vision Transformer (SubViT), a selective image tokenization method that improves fine-grained visual recognition by representing discriminative patches with multiple subto…
Fulcrum Research's Fable AI agent achieved a 7.6% improvement over the human state-of-the-art for CIFAR-10 training speed, reaching 94% accuracy in 1.828 seconds on a single A100 GPU, while Claude Opu…
Researchers proposed a hardware-aware pruning and quantization strategy for Graph Convolutional Neural Networks to adapt them for embedded FPGA platforms in event-based vision. The method achieved BRA…
Researchers proposed a controllability-observability framework for compressing deep neural networks by viewing them as nonlinear dynamical systems. The method achieved up to 83% parameter compression …
Researchers propose S-GAI, a spectral geometry-aware initialization framework for sigmoidal MLPs that encodes dataset geometry into network weights. Using SVD to extract class-wise spectral features, …
Researchers introduced Pre-Warm, a zero-training-cost method for data-conditioned initialization of the first convolutional layer in CNNs. The technique clusters patches from a single training batch t…
A new study on arXiv presents an experimental analysis of neural network-based image classification on the CIFAR-10 dataset, comparing fully connected and convolutional architectures. The convolutiona…
Researchers introduced GRAPE, a training framework that progressively exposes neural network parameters to improve adversarial robustness. On CIFAR-10 with ResNet-18, GRAPE achieved 56.94% PGD-20 robu…
Researchers introduced UtVAA, an ultra-tiny Vision Transformer architecture with a novel Affix Attention block for mobile image classification. The smallest variant has 204.67K parameters and 53.95M F…