Seguir
Jiwoo Hong
Jiwoo Hong
Dirección de correo verificada de kaist.ac.kr
Título
Citado por
Citado por
Año
ORPO: Monolithic preference optimization without reference model
J Hong, N Lee, J Thorne
EMNLP 2024, 2024
211*2024
MARL-based dual reward model on segmented actions for multiple mobile robots in automated warehouse environment
H Lee, J Hong, J Jeong
Applied Sciences 12 (9), 4703, 2022
112022
Disentangling structure and style: Political bias detection in news by inducing document hierarchy
J Hong, Y Cho, J Jung, J Han, J Thorne
Findings of EMNLP 2023, 2023
52023
Margin-aware Preference Optimization for Aligning Diffusion Models without Reference
J Hong, S Paul, N Lee, K Rasul, J Thorne, J Jeong
arXiv preprint arXiv:2406.06424, 2024
42024
각성도 및 긍/부정도의 싱글모달 사전 학습 예측 모델 기반 멀티모달 감정인식 모델
홍지우, 김예찬, 윤지영, 채소연, 한지원
한국정보과학회 학술발표논문집, 2294-2296, 2022
12022
AlphaPO--Reward shape matters for LLM alignment
A Gupta, S Tang, Q Song, S Zhu, J Hong, A Saha, V Gupta, N Lee, E Kim, ...
arXiv preprint arXiv:2501.03884, 2025
2025
Evaluating the Consistency of LLM Evaluators
N Lee, J Hong, J Thorne
COLING 2025, 2024
2024
Cross-lingual Transfer of Reward Models in Multilingual Alignment
J Hong, N Lee, R Martínez-Castaño, C Rodríguez, J Thorne
NAACL 2025, 2024
2024
Stable Language Model Pre-training by Reducing Embedding Variability
W Chung, J Hong, NM An, J Thorne, SY Yun
EMNLP 2024, 2024
2024
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–9