arxiv:2605.15726
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training & Distillation research (KAIST AI)
Recent Activity
authored a paper 2 days ago
PREPING: Building Agent Memory without Tasks authored a paper 2 days ago
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR upvoted a paper 3 days ago
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVROrganizations
None yet
models 231
Sangsang/safepath_Qwen3-32B
Text Generation • Updated • 21
Sangsang/qwen3-32B-thinksafe-32B-32-pm-3ep
Text Generation • Updated • 36
Sangsang/qwen3-32B-safechain-32-pm-3ep
Text Generation • Updated • 31
Sangsang/Qwen3-4B-Instruct-2507-GRPO_16_eps20
Text Generation • Updated • 14
Sangsang/Qwen3-4B-Instruct-2507-GRPOPE_8_eps20
Text Generation • Updated • 10
Sangsang/Qwen3-4B-Instruct-2507-GRPO_32_eps20
Text Generation • Updated • 17
Sangsang/Qwen3-4B-Instruct-2507-GRPO_8_eps20
Text Generation • Updated • 15
Sangsang/Olmo-3-7B-Instruct-SFT-ContextGRPOwDistill_2x4_eps20
Text Generation • Updated • 15
Sangsang/Olmo-3-7B-Instruct-SFT-GRPOPE_8_eps20
Text Generation • Updated • 18
Sangsang/Olmo-3-7B-Instruct-SFT-GRPO_32_eps_20
Text Generation • Updated • 17
datasets 104
Sangsang/ThinkSafe-32B-v2
Viewer • Updated • 39.9k • 130
Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 40
Sangsang/CI-Qwen3-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 8
Sangsang/CI-Qwen3-32B-Augmented-Responses
Viewer • Updated • 729 • 14
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-32B_all
Viewer • Updated • 729 • 67
Sangsang/safepath_test_2
Viewer • Updated • 39.9k • 17
Sangsang/safepath_test
Viewer • Updated • 39.9k • 18
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B_all
Viewer • Updated • 729 • 54
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-8B_all
Viewer • Updated • 729 • 90
Sangsang/CI-Olmo-3-32B-Think-Augmented-Responses
Viewer • Updated • 729 • 13