Researchers have developed a novel framework and dataset to automatically map drivable paths in challenging off-road environments, moving beyond traditional endpoint-based methods.
A new empirical study reveals the surprising effectiveness of a classic optimization technique, the Frank-Wolfe method, for crafting powerful adversarial attacks against deep learning models.
A new framework, THeGAU, boosts the performance of graph neural networks on complex data by intelligently incorporating node and edge types and strategically augmenting the graph structure.
Researchers have developed a new method for subtly manipulating machine learning models, enabling highly effective and difficult-to-detect backdoor attacks.
A new framework, AgriRegion, leverages the power of curated local knowledge to dramatically improve the accuracy and relevance of answers to agricultural questions.
A new technique empowers image generation models to learn from each other within a batch, leading to significant improvements in quality and detail.
Researchers have devised a new defense mechanism that binds a neural network to specific hardware, effectively neutralizing stolen models and bolstering security against adversarial attacks.
Researchers have developed a novel graph neural network that overcomes limitations of traditional methods to achieve improved performance in graph classification tasks.
A new approach leverages the power of graph neural networks and data augmentation within a Transformer architecture to predict how to synthesize complex molecules.
New research shows that analyzing the connections between users and content can significantly boost the accuracy of fake news detection systems.