🏢 Kim Jaechul Graduate School of AI, KAIST
Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems
·2322 words·11 mins·
loading
·
loading
Machine Learning
Deep Learning
🏢 Kim Jaechul Graduate School of AI, KAIST
Low Precision Ensembling (LPE) boosts large model accuracy using training-free ensemble creation via stochastic rounding in low-precision number systems.
Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning
·3101 words·15 mins·
loading
·
loading
AI Generated
Machine Learning
Semi-Supervised Learning
🏢 Kim Jaechul Graduate School of AI, KAIST
Boosting semi-supervised learning, a new data augmentation method using diffusion models significantly improves model accuracy, especially with mismatched data distributions.