5 papers
Reducing the Sensitivity of Neural Physics Simulators to Mesh Topology via Pretraining
Nathan Vaska, Justin Goodwin, Robin Walters +1
Meshes are used to represent complex objects in high fidelity physics simulators across a variety of domains, such as radar sensing and aerodynamics. There is growing interest in u…
Addressing Discrepancies in Semantic and Visual Alignment in Neural Networks
Natalie Abreu, Nathan Vaska, Victoria Helus
For the task of image classification, neural networks primarily rely on visual patterns. In robust networks, we would expect for visually similar classes to be represented similarl…
Evaluating the Capabilities of Multi-modal Reasoning Models with Synthetic Task Data
Nathan Vaska, Victoria Helus
The impressive advances and applications of large language and joint language-and-visual understanding models has led to an increased need for methods of probing their potential re…
Addressing Mistake Severity in Neural Networks with Semantic Knowledge
Natalie Abreu, Nathan Vaska, Victoria Helus
Robustness in deep neural networks and machine learning algorithms in general is an open research challenge. In particular, it is difficult to ensure algorithmic performance is mai…
Context-Dependent Anomaly Detection with Knowledge Graph Embedding Models
Nathan Vaska, Kevin Leahy, Victoria Helus
Increasing the semantic understanding and contextual awareness of machine learning models is important for improving robustness and reducing susceptibility to data shifts. In this…