LAMDA-SSL toolkit delivers the first unified benchmarks and robust algorithms that safely exploit unlabeled data despite ...
FPMCO decomposes multi-constraint RL into KL-projection sub-problems, achieving higher reward with lower computing than second-order rivals on the new SCIG robotics benchmark.
Recent breakthroughs in self-supervised Joint-Embedding Predictive Architectures (JEPAs) have established that regularizing Euclidean representations toward isotropic Gaussian priors yields provable ...
Abstract: With the rise of e-commerce, personalized recommendation algorithms have received much attention in recent years. Meanwhile, multimodal recommendation algorithms have become the next ...
Abstract: Existing semi-supervised learning (SSL) methods primarily rely on consistency learning to enhance model performance. However, most current approaches only validate the effectiveness of ...
Background: Maternal and child health remains a global public health issue, particularly in low- and middle-income countries where maternal and child mortality are extremely high. The World Health ...
Article Views are the COUNTER-compliant sum of full text article downloads since November 2008 (both PDF and HTML) across all institutions and individuals. These metrics are regularly updated to ...
This repository holds my completed Octave/Matlab code for the exercises in the Stanford Machine Learning course, offered on the Coursera platform.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback