Minsik Oh PRO

minsik-oh

·

https://minsik-ai.github.io/

AI & ML interests

alignment

Recent Activity

authored a paper 9 days ago

Steerable Cultural Preference Optimization of Reward Models

updated a collection 9 days ago

SCPO country reward models

upvoted a paper 9 days ago

Steerable Cultural Preference Optimization of Reward Models

View all activity

Organizations

Papers 4

arxiv:2606.18606

arxiv:2305.14299

arxiv:2302.06674

arxiv:2310.06390

models 1

minsik-oh/template-dialogue-embedding

Feature Extraction • 0.1B • Updated 9 days ago • 50 • 3

datasets 1

minsik-oh/template-dialogue-pairs

Viewer • Updated 9 days ago • 1.57M • 119 • 3