Ji Hyun Kim
YOU?
Author Swipe
View article: Alignment as Distribution Learning: Your Preference Model is Explicitly a Language Model
Alignment as Distribution Learning: Your Preference Model is Explicitly a Language Model Open
Alignment via reinforcement learning from human feedback (RLHF) has become the dominant paradigm for controlling the quality of outputs from large language models (LLMs). However, when viewed as `loss + regularization,' the standard RLHF o…
View article: Oxygen desorption kinetics of ZnO nanorod–gated AlGaN/GaN HEMT-based UV photodetectors
Oxygen desorption kinetics of ZnO nanorod–gated AlGaN/GaN HEMT-based UV photodetectors Open
In this study, we investigated the effect of gate length and surface area of the ZnO ultraviolet (UV) absorbing structure on the transient characteristics of AlGaN/GaN HEMT based UV photodetectors. The gate-areas (2, 6 and 18 μm lengths wi…
View article: Alternative methods for top quark mass measurements at the CMS
Alternative methods for top quark mass measurements at the CMS Open
The top quark mass is a fundamental parameter of the standard model and together with the W boson mass and the Higgs boson mass it provides a strong self-consistency check of the electroweak theory. Recently several new measurements of the…