3 papers
cs.AI2025
Towards Causal Representation Learning with Observable Sources as Auxiliaries
Kwonho Kim, Heejeong Nam, Inwoo Hwang +1
Causal representation learning seeks to recover latent factors that generate observational data through a mixing function. Needing assumptions on latent structures or relationships…
cs.CV2025
Compact and De-biased Negative Instance Embedding for Multi-Instance Learning on Whole-Slide Image Classification
Joohyung Lee, Heejeong Nam, Kwanhyung Lee +1
Whole-slide image (WSI) classification is a challenging task because 1) patches from WSI lack annotation, and 2) WSI possesses unnecessary variability, e.g., stain protocol. Recent…
cs.LG2024
An Adversarial Learning Approach to Irregular Time-Series Forecasting
Heejeong Nam, Jihyun Kim, Jimin Yeom
Forecasting irregular time series presents significant challenges due to two key issues: the vulnerability of models to mean regression, driven by the noisy and complex nature of t…