5 papers
Active Learning with Selective Time-Step Acquisition for PDEs
Yegon Kim, Hyunsu Kim, Gyeonghoon Ko +1
Accurately solving partial differential equations (PDEs) is critical to understanding complex scientific and engineering phenomena, yet traditional numerical solvers are computatio…
Soft Equivariance Regularization for Invariant Self-Supervised Learning
Joohyung Lee, Changhun Kim, Hyunsu Kim +2
Self-supervised learning (SSL) typically learns representations invariant to semantic-preserving augmentations. While effective for recognition, enforcing strong invariance can sup…
Axial Neural Networks for Dimension-Free Foundation Models
Hyunsu Kim, Jonggeon Park, Joan Bruna +2
The advent of foundation models in AI has significantly advanced general-purpose learning, enabling remarkable capabilities in zero-shot inference and in-context learning. However,…
Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo
Hyunsu Kim, Giung Nam, Chulhee Yun +2
Bayesian Neural Networks (BNNs) provide a promising framework for modeling predictive uncertainty and enhancing out-of-distribution robustness (OOD) by estimating the posterior dis…
Learning Infinitesimal Generators of Continuous Symmetries from Data
Gyeonghoon Ko, Hyunsu Kim, Juho Lee
Exploiting symmetry inherent in data can significantly improve the sample efficiency of a learning procedure and the generalization of learned models. When data clearly reveals und…