arxiv:2510.00492
Sangwoo Park
Sangsang
AI & ML interests
I do LLM Safety & Reasoning research (KAIST AI)
Recent Activity
updated
a model
about 20 hours ago
Sangsang/thinksafe-1.7B-n1-ablation_R32_BZ64_Gen8
published
a model
about 20 hours ago
Sangsang/thinksafe-1.7B-n1-ablation_R32_BZ64_Gen8
updated
a dataset
1 day ago
Sangsang/inference_20260110
Organizations
None yet
models
85
Sangsang/thinksafe-1.7B-n1-ablation_R32_BZ64_Gen8
Text Generation
•
Updated
•
9
Sangsang/DS_CT_20250811_LIN_1024_LOUT_4096_N100_NH100_B8_LEN_NAIVE
Text Generation
•
Updated
•
9
Sangsang/thinksafe-0.6B-n1-ablation_R32_BZ32_Gen8
Updated
Sangsang/DS_CT_20250811_LIN_1024_LOUT_4096_N200_NH800_B8_LEN_NAIVE
Text Generation
•
Updated
•
3
Sangsang/DS_CT_20250811_LIN_1024_LOUT_4096_N200_NH800_B8_LEN_PRIOR
Text Generation
•
Updated
•
7
Sangsang/DS_CT_20250811_N200_NH800_B2_LEN_PRIOR
Text Generation
•
Updated
Sangsang/DS_CT_20250811_N0_NH1000_B2_LEN_PRIOR
Text Generation
•
Updated
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-kl
Text Generation
•
Updated
•
41
Sangsang/R1-8B-thinksafe-r1-8B-ablation-32-pm-kl
Text Generation
•
Updated
•
39
Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-32-pm-kl
Text Generation
•
Updated
•
28
datasets
50
Sangsang/inference_20260110
Viewer
•
Updated
•
300
Sangsang/SOT-RL-Dataset
Viewer
•
Updated
•
11k
•
14
Sangsang/ThinkSafe-1.7B-n5_filtered_Olmo-3.1-32B-Instruct_eps10
Viewer
•
Updated
•
66.8k
•
19
Sangsang/ThinkSafe-R1-distill-1.5B-n5_filtered_Olmo-3.1-32B-Instruct_eps10
Viewer
•
Updated
•
48k
•
8
Sangsang/ThinkSafe-R1-distill-7B-n5_filtered_Olmo-3.1-32B-Instruct_eps10
Viewer
•
Updated
•
67.9k
•
12
Sangsang/ThinkSafe-R1-Distill-7B-n5_filtered_Llama-3.3-70B-Instruct_eps10
Viewer
•
Updated
•
148k
•
12
Sangsang/ThinkSafe-R1-Distill-1.5B-n5_filtered_Llama-3.3-70B-Instruct_eps10
Viewer
•
Updated
•
68.8k
•
13
Sangsang/ThinkSafe-R1-Distill-8B-n5_filtered_Llama-3.3-70B-Instruct_eps10
Viewer
•
Updated
•
154k
•
8
Sangsang/ThinkSafe-8B-n5_filtered_Olmo-3.1-32B-Instruct_eps10
Viewer
•
Updated
•
102k
•
11
Sangsang/ThinkSafe-4B-n5_filtered_Olmo-3.1-32B-Instruct_eps10
Viewer
•
Updated
•
97.5k
•
8