A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Chunming Li, Chenyang Xu, Changfeng Gui, et al.
Proposes a variational level set formulation with a distance regularization term that eliminates the need for reinitialization, enabling stable and efficient image segmentation.
Takeru Miyato, Shin‐ichi Maeda, Masanori Koyama, et al.
Virtual Adversarial Training (VAT) regularizes models by enforcing local smoothness of the label distribution via a computationally efficient, label-free adversarial direction, achieving state-of-the-art semi-supervised learning on SVHN and CIFAR-10.
Hui Zou, Trevor Hastie
The elastic net combines L1 and L2 penalties for regularization and variable selection, outperforming the lasso especially when p≫n and encouraging a grouping effect among correlated predictors.
Yueyi Liu, Chi Zhang, Sen Cui, et al.
ElasticTTT introduces a prior-preserving test-time tuning framework for video editing that prevents prior collapse via target distribution regularization, contrastive CFG, and asynchronous noise scheduling.