10 papers
Rethinking Reward Models for Multi-Domain Test-Time Scaling
Dong Bok Lee, Seanie Lee, Sangwoo Park +12
The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning…
GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer
Junmo Cho, Suhan Kim, Sangjune An +5
Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM…
FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
Seanie Lee, Sangwoo Park, Dong Bok Lee +5
Low-Rank Adaptation (LoRA), which introduces a product of two trainable low-rank matrices into frozen pre-trained weights, is widely used for efficient fine-tuning of language mode…
Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning
Dong Bok Lee, Aoxuan Silvia Zhang, Byungjoo Kim +5
In this paper, we address the problem of \emph{cost-sensitive} hyperparameter optimization (HPO) built upon freeze-thaw Bayesian optimization (BO). Specifically, we assume a scenar…
Automated Structured Radiology Report Generation with Rich Clinical Context
Seongjae Kang, Dong Bok Lee, Juho Jung +3
Automated structured radiology report generation (SRRG) from chest X-ray images offers significant potential to reduce workload of radiologists by generating reports in structured…
PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models
Seongjae Kang, Dong Bok Lee, Hyungjoon Jang +2
Knowledge distillation (KD) is a widely used framework for training compact, task-specific models by transferring the knowledge from teacher models. However, its application to act…