Dong Bok Lee

Rethinking Reward Models for Multi-Domain Test-Time Scaling

Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization

Automated Structured Radiology Report Generation with Rich Clinical Context

PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Langauge Models

FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning

Dimension Agnostic Neural Processes

Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks

Cost-Sensitive Multi-Fidelity Bayesian Optimization