5 papers
SpectraQuery: A Hybrid Retrieval-Augmented Conversational Assistant for Battery Science
Sreya Vangara, Jagjit Nanda, Yan-Kai Tzeng +1
Scientific reasoning increasingly requires linking structured experimental data with the unstructured literature that explains it, yet most large language model (LLM) assistants ca…
Physically Interpretable Representation Learning with Gaussian Mixture Variational AutoEncoder (GM-VAE)
Tiffany Fan, Murray Cutforth, Marta D'Elia +3
Extracting compact, physically interpretable representations from high-dimensional scientific data is a persistent challenge due to the complex, nonlinear structures inherent in ph…
Multi-fidelity Batch Active Learning for Gaussian Process Classifiers
Murray Cutforth, Yiming Yang, Tiffany Fan +2
Many science and engineering problems rely on expensive computational simulations, where a multi-fidelity approach can accelerate the exploration of a parameter space. We study eff…
Bi-fidelity Interpolative Decomposition for Multimodal Data
Murray Cutforth, Tiffany Fan, Tony Zahtila +2
Multi-fidelity simulation is a widely used strategy to reduce the computational cost of many-query numerical simulation tasks such as uncertainty quantification, design space explo…
Physically Interpretable Representation and Controlled Generation for Turbulence Data
Tiffany Fan, Murray Cutforth, Marta D'Elia +3
Computational Fluid Dynamics (CFD) plays a pivotal role in fluid mechanics, enabling precise simulations of fluid behavior through partial differential equations (PDEs). However, t…