Seanie Lee

5

Papers

84

Total Citations

1

Affiliations

Affiliations

KAIST

Papers (5)

Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning

DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models

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

Distilling LLM Agent into Small Models with Retrieval and Code Tools

Drug Discovery with Dynamic Goal-aware Fragments