arxiv:2605.29250
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training & Distillation research (KAIST AI)
Recent Activity
published a model 1 day ago
Sangsang/ThinkSafe-Qwen3-8B-ICL-LoRA updated a model 1 day ago
Sangsang/ThinkSafe-Qwen3-8B-ICL-LoRA published a model 2 days ago
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-Activation-LoRAOrganizations
None yet
models 252
Sangsang/ThinkSafe-Qwen3-8B-ICL-LoRA
Text Generation • Updated • 16
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-Activation-LoRA
Text Generation • Updated • 31
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-ICL-LoRA
Text Generation • Updated • 21
Sangsang/ThinkSafe-Qwen3-8B-Activation-LoRA
Text Generation • Updated • 19
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 16
Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 7
Sangsang/R1-8B-thinksafe-r1-8B-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 7
Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 15
Sangsang/qwen3-0.6B-thinksafe-0.6B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 9
Sangsang/R1-7B-thinksafe-r1-7B-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 8
datasets 111
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-Activation-data
Viewer • Updated • 38.5k • 19
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-ICL-data
Viewer • Updated • 39.3k • 19
Sangsang/ThinkSafe-Qwen3-8B-Activation-data
Viewer • Updated • 38.8k • 22
Sangsang/ThinkSafe-Qwen3-8B-ICL-data
Viewer • Updated • 39.4k • 20
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B_Holistic
Viewer • Updated • 729 • 25
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B-Instruct-2507_Holistic
Viewer • Updated • 729 • 17
Sangsang/movie_tv_Qwen3_32B
Viewer • Updated • 17.1k • 11
Sangsang/ThinkSafe-32B-v2
Viewer • Updated • 39.9k • 9
Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 12
Sangsang/CI-Qwen3-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 21