arxiv:2609.34327
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training & Distillation research (KAIST AI)
Recent Activity
upvoted a paper about 7 hours ago
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents published a model about 22 hours ago
Sangsang/rewind-run1-sft-model published a dataset about 22 hours ago
Sangsang/rewind-run1-sft-dataOrganizations
None yet
models 253
Sangsang/rewind-run1-sft-model
Text Generation • 2B • Updated
Sangsang/ThinkSafe-Qwen3-8B-ICL-LoRA
Text Generation • Updated • 26
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-Activation-LoRA
Text Generation • Updated • 47
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-ICL-LoRA
Text Generation • Updated • 35
Sangsang/ThinkSafe-Qwen3-8B-Activation-LoRA
Text Generation • Updated • 28
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 15
Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 10
Sangsang/R1-8B-thinksafe-r1-8B-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 11
Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 16
Sangsang/qwen3-0.6B-thinksafe-0.6B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 13
datasets 112
Sangsang/rewind-run1-sft-data
Viewer • Updated • 584
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-Activation-data
Viewer • Updated • 38.5k • 45
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-ICL-data
Viewer • Updated • 39.3k • 47
Sangsang/ThinkSafe-Qwen3-8B-Activation-data
Viewer • Updated • 38.8k • 35
Sangsang/ThinkSafe-Qwen3-8B-ICL-data
Viewer • Updated • 39.4k • 33
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B_Holistic
Viewer • Updated • 729 • 18
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B-Instruct-2507_Holistic
Viewer • Updated • 729 • 12
Sangsang/movie_tv_Qwen3_32B
Viewer • Updated • 17.1k • 12
Sangsang/ThinkSafe-32B-v2
Viewer • Updated • 39.9k • 10
Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 23