Jeewoo Kim's picture

4 1 9

Jeewoo Kim

jdubkim

·

jdubkim

AI & ML interests

LLM (Reasoning, RLHF) Trust and Safety

Organizations

models 2

jdubkim/Qwen2-0.5B-GRPO-test

Updated Jun 14, 2025

jdubkim/ppo-LunarLander-v2-TEST

Reinforcement Learning • Updated Dec 20, 2022 • 1

datasets 4

jdubkim/ScreenSpot-v2

Viewer • Updated Oct 29, 2025 • 1.27k • 7

jdubkim/ScreenSpot-Pro

Viewer • Updated Aug 4, 2025 • 1.58k • 12

jdubkim/OSWorld-G

Viewer • Updated Aug 1, 2025 • 564 • 7

jdubkim/OSWorld-G-refined

Viewer • Updated Aug 1, 2025 • 564 • 6