arxiv:2605.29250
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training & Distillation research (KAIST AI)
Recent Activity
authored a paper about 20 hours ago
OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources updated a model about 22 hours ago
Sangsang/rlsd_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-06_mcl8192_within_batch updated a model about 22 hours ago
Sangsang/rlsd_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-06_mcl8192_within_batchOrganizations
None yet
models 241
Sangsang/rlsd_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-06_mcl8192_within_batch
Text Generation • Updated
Sangsang/rlsd_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-06_mcl8192_within_batch
Text Generation • Updated
Sangsang/rlsd_Qwen3-4B_lora32_n2048_seed42_lr1e-06_mcl16384_within_batch
Text Generation • Updated
Sangsang/sdpo_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-05_mcl8192_full_voacb
Text Generation • Updated
Sangsang/sdpo_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-05_mcl8192_full_voacb
Text Generation • Updated
Sangsang/sdpo_Qwen3-4B_lora32_n2048_seed42_lr1e-05_mcl16384_full_voacb
Text Generation • Updated
Sangsang/grpo_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-05_mcl8192
Text Generation • Updated
Sangsang/grpo_Qwen3-4B-Instruct-2507_lora32_n2048_seed42_lr1e-06_mcl8192
Text Generation • Updated
Sangsang/grpo_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-06_mcl8192
Text Generation • Updated
Sangsang/grpo_Qwen3-4B_lora32_n2048_seed42_lr1e-06_mcl16384
Text Generation • Updated
datasets 104
Sangsang/ThinkSafe-32B-v2
Viewer • Updated • 39.9k • 137
Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 39
Sangsang/CI-Qwen3-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 9
Sangsang/CI-Qwen3-32B-Augmented-Responses
Viewer • Updated • 729 • 15
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-32B_all
Viewer • Updated • 729 • 81
Sangsang/safepath_test_2
Viewer • Updated • 39.9k • 15
Sangsang/safepath_test
Viewer • Updated • 39.9k • 13
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B_all
Viewer • Updated • 729 • 57
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-8B_all
Viewer • Updated • 729 • 87
Sangsang/CI-Olmo-3-32B-Think-Augmented-Responses
Viewer • Updated • 729 • 13