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 5 days ago

12kimih/r1qa-revised-rollouts

updated a model 7 days ago

12kimih/Qwen3-4B-r1qa-v1

published a model 7 days ago

12kimih/Qwen3-4B-r1qa-v1

View all activity

Organizations

None yet

models 4

12kimih/Qwen3-4B-r1qa-v1

Text Generation • 4B • Updated 7 days ago • 27

12kimih/Qwen3-0.6B-r1qa-grpo-v0

Text Generation • 0.6B • Updated 25 days ago • 31

12kimih/Qwen3-0.6B-r1qa-gpt-oss-v0

Text Generation • 0.6B • Updated 25 days ago • 17

12kimih/Llama-3.2-3B-HiCUPID

datasets 7

12kimih/r1qa-revised-rollouts

Viewer • Updated 5 days ago • 99.7k • 41

12kimih/r1qa-raw-rollouts

Viewer • Updated 9 days ago • 99.7k • 108

12kimih/r1qa-guided-rollouts

Viewer • Updated 21 days ago • 1.08M • 198

12kimih/r1qa-benchmarks

Viewer • Updated Oct 14 • 300k • 82

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

Viewer • Updated Sep 12 • 2.97k • 20

12kimih/r1qa-clip-with-perplexity

Viewer • Updated Sep 9 • 2.97k • 33

12kimih/HiCUPID

Viewer • Updated Jun 3 • 918k • 130