6 24 29

Sangwoo Park

Sangsang

sangwoopark000312

AI & ML interests

I do LLM Safety & Reasoning research (KAIST AI)

Recent Activity

updated a collection about 1 hour ago

Qwen3-0.6B-thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8

updated a collection about 1 hour ago

Qwen3-0.6B-thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8

updated a model about 1 hour ago

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-7500

View all activity

Organizations

None yet

Collections 1

Papers 3

arxiv:2510.00492

arxiv:2505.12805

arxiv:2503.07216

models 97

datasets 49

Sangsang/SOT-RL-Dataset

Viewer • Updated 4 days ago • 11k • 14

Sangsang/ThinkSafe-1.7B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated 13 days ago • 66.8k • 15

Sangsang/ThinkSafe-R1-distill-1.5B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated 14 days ago • 48k • 7

Sangsang/ThinkSafe-R1-distill-7B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated 14 days ago • 67.9k • 12

Sangsang/ThinkSafe-R1-Distill-7B-n5_filtered_Llama-3.3-70B-Instruct_eps10

Viewer • Updated 16 days ago • 148k • 12

Sangsang/ThinkSafe-R1-Distill-1.5B-n5_filtered_Llama-3.3-70B-Instruct_eps10

Viewer • Updated 16 days ago • 68.8k • 12

Sangsang/ThinkSafe-R1-Distill-8B-n5_filtered_Llama-3.3-70B-Instruct_eps10

Viewer • Updated 16 days ago • 154k • 8

Sangsang/ThinkSafe-8B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated 16 days ago • 102k • 8

Sangsang/ThinkSafe-4B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated 16 days ago • 97.5k • 5

Sangsang/ThinkSafe-R1-Distill-8B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated 16 days ago • 77.1k • 10

View 49 datasets

Sangwoo Park

AI & ML interests

Recent Activity

Organizations

Collections 1

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-500

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-1000

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-1500

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-2000

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-500

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-1000

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-1500

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-2000

Papers 3

models 97

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-7500

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-7000

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-6500

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-6000

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-5500

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-5000

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-4500

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-4000

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-3500

Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8_checkpoint-3000

datasets 49

Sangsang/SOT-RL-Dataset

Sangsang/ThinkSafe-1.7B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Sangsang/ThinkSafe-R1-distill-1.5B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Sangsang/ThinkSafe-R1-distill-7B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Sangsang/ThinkSafe-R1-Distill-7B-n5_filtered_Llama-3.3-70B-Instruct_eps10

Sangsang/ThinkSafe-R1-Distill-1.5B-n5_filtered_Llama-3.3-70B-Instruct_eps10

Sangsang/ThinkSafe-R1-Distill-8B-n5_filtered_Llama-3.3-70B-Instruct_eps10

Sangsang/ThinkSafe-8B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Sangsang/ThinkSafe-4B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Sangsang/ThinkSafe-R1-Distill-8B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Sangwoo Park

AI & ML interests

Recent Activity

Organizations

Collections 1

Papers 3

models 97 Sort: Recently updated

datasets 49 Sort: Recently updated

models 97

datasets 49