5 papers
Modularity-Free Conflict-Averse Training for Generalized PINNs
Heejo Kong, Beomchul Park, Sung-Jin Kim +1
Physics-informed neural networks (PINNs) have become a powerful framework for solving PDEs by embedding physical laws into differentiable objectives. Despite their advances, traini…
Compositional Meta-Learning for Mitigating Task Heterogeneity in Physics-Informed Neural Networks
Beomchul Park, Minsu Koh, Heejo Kong +1
Physics-informed neural networks (PINNs) approximate solutions of partial differential equations (PDEs) by embedding physical laws into the loss function. In parameterized PDE fami…
Text-guided Weakly Supervised Framework for Dynamic Facial Expression Recognition
Gunho Jung, Heejo Kong, Seong-Whan Lee
Dynamic facial expression recognition (DFER) aims to identify emotional states by modeling the temporal changes in facial movements across video sequences. A key challenge in DFER…
Diversify and Conquer: Open-set Disagreement for Robust Semi-supervised Learning with Outliers
Heejo Kong, Sung-Jin Kim, Gunho Jung +1
Conventional semi-supervised learning (SSL) ideally assumes that labeled and unlabeled data share an identical class distribution, however in practice, this assumption is easily vi…
Integrating Locality-Aware Attention with Transformers for General Geometry PDEs
Minsu Koh, Beom-Chul Park, Heejo Kong +1
Neural operators have emerged as promising frameworks for learning mappings governed by partial differential equations (PDEs), serving as data-driven alternatives to traditional nu…