3 papers
cs.LG2026
Hierarchical Scaffolding Enables Human-Like Cognitive Selectivity under Data Scarcity
Juhyoung Park, Jaehyuk Bae, Hyeonbo Yang +1
Modern machine learning systems demand extensive datasets for visual recognition. Conversely, humans learn with high efficiency despite severe data limitations, often by acquiring…
cs.LG2025
One-Time Soft Alignment Enables Resilient Learning without Weight Transport
Jeonghwan Cheon, Jaehyuk Bae, Se-Bum Paik
Backpropagation is the cornerstone of deep learning, but its reliance on symmetric weight transport and global synchronization makes it computationally expensive and biologically i…
cs.LG2024
Pretraining with random noise for uncertainty calibration
Jeonghwan Cheon, Se-Bum Paik
Uncertainty calibration is crucial for various machine learning applications, yet it remains challenging. Many models exhibit hallucinations - confident yet inaccurate responses -…