Hybrid Transformer-Mamba Architecture for Weakly Supervised Volumetric Medical Segmentation

ZK APEX introduces a zero-shot personalized unlearning method that allows models to forget specific data points without retraining, addressing privacy and compliance challenges in machine learning. This method combines sparse masking and a compensation step to ensure that personalized models can effectively forget targeted samples while maintaining local utility.

The empirical evaluation of Frank-Wolfe methods for constructing white-box adversarial attacks highlights the need for efficient adversarial attack construction in neural networks, particularly focusing on numerical optimization techniques. The study emphasizes the application of modified Frank-Wolfe methods to enhance the robustness of neural networks against adversarial threats, utilizing datasets like MNIST and CIFAR-10 for testing.

A recent study has introduced a hierarchical attention model for detecting sparse volumetric anomalies in subclinical keratoconus using three-dimensional anterior segment optical coherence tomography (AS-OCT). This model outperformed traditional convolutional neural networks (CNNs) and global-attention Vision Transformers (ViTs) by achieving 21-23% higher sensitivity and specificity in identifying subtle abnormalities.

A new study has developed an optimized deep learning pipeline for automated fish re-identification using the AutoFish dataset, which simulates Electronic Monitoring systems with conveyor belts featuring six similar fish species. The research demonstrates significant improvements in key metrics, achieving a peak performance of 41.65% mAP@k and 90.43% Rank-1 accuracy through advanced techniques like hard triplet mining and a custom image transformation pipeline.