collaborators

6 papers

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks

Dongwoo Lee, Dong Bok Lee, Steven Adriaensen +5

Scaling has been a major driver of recent advancements in deep learning. Numerous empirical studies have found that scaling laws often follow the power-law and proposed several var…

cs.CL2025

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models

Seanie Lee, Dong Bok Lee, Dominik Wagner +5

Deploying large language models (LLMs) in real-world applications requires robust safety guard models to detect and block harmful user prompts. While large safety guard models achi…

cs.CL2025

Learning diverse attacks on large language models for robust red-teaming and safety tuning

Seanie Lee, Minsu Kim, Lynn Cherif +8

Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs). Developing ef…

cs.CL2025

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

Seanie Lee, Haebin Seong, Dong Bok Lee +6

Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world appli…