arxiv:2601.23143
Sangwoo Park
Sangsang
AI & ML interests
I do LLM Safety & Reasoning research (KAIST AI)
Recent Activity
authored
a paper
2 days ago
THINKSAFE: Self-Generated Safety Alignment for Reasoning Models
updated
a dataset
3 days ago
Sangsang/SOT-RL-Dataset-Modified
published
a dataset
3 days ago
Sangsang/SOT-RL-Dataset-Modified
Organizations
None yet
models
149
Sangsang/thinksafe-r1-1.5B-ablation_R32_BZ64_Gen8
Text Generation
•
Updated
•
11
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-e3
Text Generation
•
Updated
•
51
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-e2
Text Generation
•
Updated
•
34
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-16-pm-e3
Text Generation
•
Updated
•
28
Sangsang/R1-8B-thinksafe-r1-8B-ablation-32-pm-e3
Text Generation
•
Updated
•
13
Sangsang/R1-8B-thinksafe-r1-8B-ablation-32-pm-e2
Text Generation
•
Updated
•
12
Sangsang/R1-8B-thinksafe-r1-8B-ablation-16-pm-e3
Text Generation
•
Updated
•
21
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-16-pm-e2
Text Generation
•
Updated
•
45
Sangsang/R1-8B-thinksafe-r1-8B-ablation-16-pm-e2
Text Generation
•
Updated
•
10
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-16-pm-e1
Text Generation
•
Updated
•
30
datasets
65
Sangsang/SOT-RL-Dataset-Modified
Viewer
•
Updated
•
11k
•
25
Sangsang/ThinkSafe-R1-Distill-8B-ablation-math-all
Viewer
•
Updated
•
34.7k
•
7
Sangsang/ThinkSafe-R1-Distill-7B-ablation-math-all
Viewer
•
Updated
•
34.9k
•
4
Sangsang/ThinkSafe-R1-Distill-1.5B-ablation-math-all
Viewer
•
Updated
•
28.5k
•
4
Sangsang/ThinkSafe-8B-n1-ablation-math-all
Viewer
•
Updated
•
32.2k
•
5
Sangsang/ThinkSafe-4B-n1-ablation-math-all
Viewer
•
Updated
•
32.7k
•
3
Sangsang/ThinkSafe-1.7B-n1-ablation-math-all
Viewer
•
Updated
•
31.2k
•
3
Sangsang/ThinkSafe-0.6B-n1-ablation-math-all
Viewer
•
Updated
•
29.9k
•
1
Sangsang/ThinkSafe-R1-Distill-8B-ablation-math-16k
Viewer
•
Updated
•
27.4k
•
5
Sangsang/ThinkSafe-R1-Distill-7B-ablation-math-16k
Viewer
•
Updated
•
28.3k
•
3