Sangwoo Park's picture

Sangwoo Park

Sangsang

·

sangwoopark000312

AI & ML interests

I do LLM Safety & Reasoning research (KAIST AI)

Recent Activity

updated a model 3 days ago

Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-e3

published a model 3 days ago

Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-e3

updated a model 3 days ago

Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-e2

View all activity

Organizations

None yet

Sangsang 's datasets 50

Sangsang/inference_20260110

Viewer • Updated 10 days ago • 300 • 19

Sangsang/SOT-RL-Dataset

Viewer • Updated 18 days ago • 11k • 16

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

Viewer • Updated 27 days ago • 66.8k • 20

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

Viewer • Updated 28 days ago • 48k • 10

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

Viewer • Updated 28 days ago • 67.9k • 15

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

Viewer • Updated 30 days ago • 148k • 8

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

Viewer • Updated 30 days ago • 68.8k • 8

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

Viewer • Updated 30 days ago • 154k • 2

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

Viewer • Updated about 1 month ago • 102k • 5

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

Viewer • Updated about 1 month ago • 97.5k • 4

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

Viewer • Updated about 1 month ago • 77.1k • 8

Sangsang/ThinkSafe-0.6B-n5_filtered_Olmo-3.1-32B-Instruct_eps10

Viewer • Updated about 1 month ago • 33k • 5

Sangsang/ThinkSafe-mixed-0.6B-8B

Viewer • Updated Dec 20, 2025 • 39.8k • 6

Sangsang/ThinkSafe-mixed-0.6B-4B

Viewer • Updated Dec 20, 2025 • 39.8k • 3

Sangsang/ThinkSafe-mixed-0.6B-1.7B

Viewer • Updated Dec 20, 2025 • 38.9k • 2

Sangsang/thinksafe_r1-distill_1.5B_force_2_harmful-refusal

Viewer • Updated Nov 26, 2025 • 34.9k • 2

Sangsang/thinksafe_r1-distill_1.5B_force_1_harmful-refusal

Viewer • Updated Nov 26, 2025 • 34.7k • 1

Sangsang/thinksafe_r1-distill_1.5B_force_2_harmful

Viewer • Updated Nov 26, 2025 • 38.6k

Sangsang/thinksafe_r1-distill_1.5B_force_1_harmful

Viewer • Updated Nov 26, 2025 • 38.6k

Sangsang/thinksafe_r1-distill_1.5B_forcing_3_debug

Viewer • Updated Nov 25, 2025 • 62

Sangsang/thinksafe_r1-distill_1.5B_forcing_2_debug

Viewer • Updated Nov 25, 2025 • 62

Sangsang/ThinkSafe-4B-n5-refusal_20000_5

Viewer • Updated Nov 22, 2025 • 235k • 1

Sangsang/ThinkSafe-0.6B-n5-refusal_20000_5

Viewer • Updated Nov 22, 2025 • 204k • 2

Sangsang/ThinkSafe-R1-Distill-7B-n5-refusal_20000_5

Viewer • Updated Nov 21, 2025 • 261k • 3

Sangsang/ThinkSafe-R1-Distill-1.5B-n5-refusal_20000_5

Viewer • Updated Nov 21, 2025 • 204k • 1

Sangsang/thinksafe-r1-distill-1.5B-n5_filtered_all_deepseekr-preview_5000_5

Viewer • Updated Nov 19, 2025 • 184k • 2

Sangsang/r1-8B_deepseekr-preview_5000_5

Viewer • Updated Nov 19, 2025 • 25k

Sangsang/r1-7B_deepseekr-preview_5000_5

Viewer • Updated Nov 19, 2025 • 25k

Sangsang/r1-1.5B_deepseekr-preview_5000_5

Viewer • Updated Nov 19, 2025 • 25k

Sangsang/thinksafe-r1-distill-8B-n5-filtered-all

Viewer • Updated Nov 17, 2025 • 191k • 1