arxiv:2609.34327
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training & Distillation research (KAIST AI)
Recent Activity
upvoted a paper about 1 hour ago
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery upvoted a paper about 21 hours ago
Follow the Entities: A Corpus Map for Agentic Search authored a paper 2 days ago
Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric KnowledgeOrganizations
None yet
models 252
Sangsang/ThinkSafe-Qwen3-8B-ICL-LoRA
Text Generation • Updated • 21
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-Activation-LoRA
Text Generation • Updated • 40
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-ICL-LoRA
Text Generation • Updated • 29
Sangsang/ThinkSafe-Qwen3-8B-Activation-LoRA
Text Generation • Updated • 22
Sangsang/qwen3-8B-thinksafe-8B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 18
Sangsang/qwen3-4B-thinksafe-4B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 11
Sangsang/R1-8B-thinksafe-r1-8B-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 10
Sangsang/qwen3-1.7B-thinksafe-1.7B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 19
Sangsang/qwen3-0.6B-thinksafe-0.6B-n1-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 11
Sangsang/R1-7B-thinksafe-r1-7B-ablation-32-pm-3ep-harmful_only
Text Generation • Updated • 10
datasets 111
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-Activation-data
Viewer • Updated • 38.5k • 35
Sangsang/ThinkSafe-DeepSeek-R1-Distill-Llama-8B-ICL-data
Viewer • Updated • 39.3k • 34
Sangsang/ThinkSafe-Qwen3-8B-Activation-data
Viewer • Updated • 38.8k • 32
Sangsang/ThinkSafe-Qwen3-8B-ICL-data
Viewer • Updated • 39.4k • 28
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B_Holistic
Viewer • Updated • 729 • 19
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B-Instruct-2507_Holistic
Viewer • Updated • 729 • 14
Sangsang/movie_tv_Qwen3_32B
Viewer • Updated • 17.1k • 11
Sangsang/ThinkSafe-32B-v2
Viewer • Updated • 39.9k • 8
Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 16
Sangsang/CI-Qwen3-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 11