5 papers
Reduced Order Modeling of Energetic Materials Using Physics-Aware Recurrent Convolutional Neural Networks in a Latent Space (LatentPARC)
Zoë J. Gray, Joseph B. Choi, Youngsoo Choi +3
Physics-aware deep learning (PADL) has gained popularity for use in complex spatiotemporal dynamics (field evolution) simulations, such as those that arise frequently in computatio…
Point-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Clouds
Gunner Stone, Youngsook Choi, Alireza Tavakkoli +1
Pre-training strategies play a critical role in advancing the performance of transformer-based models for 3D point cloud tasks. In this paper, we introduce Point-RTD (Replaced Toke…
Rollout-LaSDI: Enhancing the long-term accuracy of Latent Space Dynamics
Robert Stephany, Youngsoo Choi
Solving complex partial differential equations is vital in the physical sciences, but often requires computationally expensive numerical methods. Reduced-order models (ROMs) addres…
Reducing Frequency Bias of Fourier Neural Operators in 3D Seismic Wavefield Simulations Through Multi-Stage Training
Qingkai Kong, Caifeng Zou, Youngsoo Choi +5
The recent development of Neural Operator (NeurOp) learning for solutions to the elastic wave equation shows promising results and provides the basis for fast large-scale simulatio…
Quantifying Qualitative Insights: Leveraging LLMs to Market Predict
Hoyoung Lee, Youngsoo Choi, Yuhee Kwon
Recent advancements in Large Language Models (LLMs) have the potential to transform financial analytics by integrating numerical and textual data. However, challenges such as insuf…