Sangwoo Park

Sangsang

7 38 30

AI & ML interests

I do LLM post-training & Distillation research (KAIST AI)

Recent Activity

updated a model 9 days ago

Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only

published a model 9 days ago

Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only

updated a model 9 days ago

Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-32-pm-3ep-harmful_only

View all activity

Organizations

None yet

liked a dataset 5 months ago

google/IFEval

Viewer • Updated Aug 14, 2024 • 541 • 106k • 161

liked a Space 9 months ago

Unlocking On-Policy Distillation for Any Model Family

📝

119

Explore on-policy distillation visualization for any model

liked a model 9 months ago

openai/gpt-oss-safeguard-20b

Text Generation • 22B • Updated Jan 14 • 103k • • 245

liked a model 12 months ago

unsloth/Qwen2.5-1.5B-Instruct

Text Generation • 2B • Updated Feb 6, 2025 • 43.1k • 9

liked a dataset about 1 year ago

Rowan/hellaswag

Viewer • Updated Jul 10, 2025 • 60k • 299k • 188

liked a model about 1 year ago

Goodfire/DeepSeek-R1-SAE-l37

Updated Apr 21, 2025 • 20

liked 2 datasets about 1 year ago

open-r1/OpenR1-Math-220k

Viewer • Updated Feb 18, 2025 • 450k • 56.6k • 779

AI-MO/NuminaMath-1.5

Viewer • Updated Jan 29 • 896k • 9.87k • 191

liked a model about 1 year ago

qresearch/DeepSeek-R1-Distill-Llama-8B-SAE-l19

Updated Jan 25, 2025 • 8

liked a dataset about 1 year ago

launch/thinkprm-1K-verification-cots

Viewer • Updated Apr 18 • 1k • 89 • 8

liked a Space about 1 year ago

Scaling test-time compute

📈

601

Boost LLM answers with flexible test‑time search strategies

liked 3 models about 1 year ago

liked a model over 1 year ago

Qwen/Qwen2.5-0.5B-Instruct

Text Generation • 0.5B • Updated Sep 25, 2024 • 6.56M • • 576

liked a dataset over 1 year ago

reglab/legal_hallucinations

Preview • Updated Jun 4, 2024 • 67 • 10

liked 3 models over 1 year ago

Qwen/Qwen2.5-Math-7B-Instruct

Text Generation • 8B • Updated Sep 23, 2024 • 67.9k • • 90

meta-llama/Llama-3.1-8B

Text Generation • 8B • Updated Oct 16, 2024 • 1.52M • • 2.35k

Qwen/Qwen2.5-Math-7B

Text Generation • 8B • Updated Sep 23, 2024 • 134k • • 116