Ik-hwan Kim's picture

11

Ik-hwan Kim

12kimih

·

https://github.com/12kimih

AI & ML interests

Large Language Models, Reinforcement Learning, Multimodal AI, AI Agents, Mechanistic Interpretability

Recent Activity

updated a dataset 4 days ago

12kimih/r1qa-refined-rollouts

updated a model 4 days ago

12kimih/Qwen3-0.6B-r1qa-v1

published a model 4 days ago

12kimih/Qwen3-0.6B-r1qa-v1

View all activity

Organizations

None yet

12kimih 's datasets 8

12kimih/r1qa-refined-rollouts

Viewer • Updated 4 days ago • 633k • 117

12kimih/r1qa-2wikimultihopqa

Viewer • Updated 7 days ago • 1.08M • 22

12kimih/r1qa-musique

Viewer • Updated 7 days ago • 134k • 12

12kimih/r1qa-hotpotqa

Viewer • Updated 7 days ago • 587k • 47

12kimih/r1qa-guided-rollouts

Viewer • Updated Nov 19, 2025 • 1.08M • 878

12kimih/r1qa-clip-and-guide-using-Qwen3-8B

Viewer • Updated Sep 12, 2025 • 2.97k • 15

12kimih/r1qa-clip-with-perplexity

Viewer • Updated Sep 9, 2025 • 2.97k • 18

12kimih/HiCUPID

Viewer • Updated Jun 3, 2025 • 918k • 142