Latest Articles for Machine Learning

JADS combines theme discovery and summarization for clear text insights.

Examining how in-distribution labels impact out-of-distribution detection in machine learning.

This study improves the security of quantum machine learning against adversarial attacks through noise channels and privacy methods.

A framework improves GNNs by using text attributes in graph structures.

Introducing new methods for complex optimization problems on curved spaces.

A new method to improve predictive models using uncertain data.

A new approach enhances prompt diversity for safer language models.

Exploring how transformers tackle various graph reasoning tasks effectively.

VLMs struggle with image classification, but better data integration can enhance their capabilities.

Exploring the role of gradient descent in stochastic optimization and its implications for sample size.

New framework improves image recognition across different domains using language descriptions.

Exploring efficient training methods for large machine learning models.

Exploring new methods for designing frames in machine learning.

A new method improves model accuracy with simple adjustments.

A new method improves facial landmark detection without labeled data.

Self-supervised learning enhances handwriting verification accuracy using unlabeled data.

Combining tensor completion with uncertainty quantification for better data insights.

Strategies to enhance the learning of knowledge in language models.

Introducing ToCa, a method to create captions using only text data.

COUP improves algorithm configuration by efficiently exploring parameter spaces.

A new approach to enhance array performance in programming.

A new approach combines machine learning with physics to improve EDX data interpretation.

This article discusses methods used to address unknown data in various fields.

Exploring how inter-concept relationships can enhance AI system transparency.

A novel approach helps robots connect visual data with actions.

TSRMs offer a new way to analyze time series data effectively.

A new benchmark for evaluating fairness in representation learning methods.

A novel approach enhances classification accuracy by reducing background reliance.

Understanding and mitigating hallucination in AI for reliable performance.

Introducing MAGE: an innovative approach to explain Graph Neural Networks in chemistry.

Analyzing how LoRA affects knowledge retention in pretrained models during continual learning.

Discover new techniques to improve efficiency in deep neural network training.

Fast-FedUL provides quick data removal methods for federated learning while ensuring privacy.

New framework improves predictions by analyzing interconnected data series.

A look into neural collapse and its impact on deep learning models.

A novel approach employs graph convolutional networks for efficient music data analysis.

A study on how user clustering improves recommendation algorithm performance.

This article discusses extending context windows in language models using positional vectors.

VeLoRA optimizes memory use in training large models without losing performance.

This article examines security risks of backdoor attacks on machine learning in graph systems.