Ik-hwan Kim

12kimih

11

·

https://github.com/12kimih

AI & ML interests

Large Language Models, Reinforcement Learning, Reasoning, Agentic AI

Recent Activity

updated a dataset 6 days ago

12kimih/intellect-3-rl-math-5k

published a dataset 6 days ago

12kimih/intellect-3-rl-math-5k

updated a dataset 7 days ago

12kimih/intellect-3-rl-math-decontaminated

View all activity

Organizations

models 1

12kimih/Llama-3.2-3B-HiCUPID

Updated Jun 3, 2025

datasets 7

12kimih/intellect-3-rl-math-5k

Viewer • Updated 6 days ago • 5k • 37

12kimih/intellect-3-rl-math-decontaminated

Viewer • Updated 7 days ago • 20.9k • 33

12kimih/nemotron-math-v2-hard

Viewer • Updated Apr 16 • 34.1k • 42

12kimih/nemotron-math-v2-medium

Viewer • Updated Apr 16 • 40.3k • 34

12kimih/nemotron-math-v2-easy

Viewer • Updated Apr 16 • 85.4k • 35

12kimih/frames-benchmark

Viewer • Updated Jan 14 • 801 • 12

12kimih/HiCUPID

Viewer • Updated Jun 3, 2025 • 918k • 86