Sangwoo Park's picture

Sangwoo Park

Sangsang

·

swgger

AI & ML interests

I do LLM post-training research (KAIST AI)

Recent Activity

updated a model 4 days ago

Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p75_fw0p25_ema0p999_ep30

published a model 4 days ago

Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p75_fw0p25_ema0p999_ep30

updated a model 4 days ago

Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p25_fw0p75_ema0p999_ep30

View all activity

Organizations

None yet

Sangsang 's datasets 103

Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses

Viewer • Updated 16 days ago • 729 • 33

Sangsang/CI-Qwen3-32B-Instruct-Augmented-Responses

Viewer • Updated 16 days ago • 729 • 31

Sangsang/CI-Qwen3-32B-Augmented-Responses

Viewer • Updated 16 days ago • 729 • 59

Sangsang/ContextualIntegritySyntheticDataset_Qwen3-32B_all

Viewer • Updated 19 days ago • 729 • 60

Sangsang/safepath_test_2

Viewer • Updated 29 days ago • 39.9k • 31

Sangsang/safepath_test

Viewer • Updated 29 days ago • 39.9k • 33

Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B_all

Viewer • Updated 30 days ago • 729 • 88

Sangsang/ContextualIntegritySyntheticDataset_Qwen3-8B_all

Viewer • Updated 30 days ago • 729 • 37

Sangsang/CI-Olmo-3-32B-Think-Augmented-Responses

Viewer • Updated about 1 month ago • 729 • 28

Sangsang/ContextualIntegritySyntheticDataset_Olmo-3-32B-Think_all

Viewer • Updated about 1 month ago • 729 • 30

Sangsang/Qwen3-8B-thinksafe-unfiltered-raw

Viewer • Updated about 1 month ago • 40k • 29

Sangsang/DeepSeek-R1-Distill-Llama-8B-thinksafe-unfiltered-raw

Viewer • Updated Mar 26 • 40k • 29

Sangsang/CI-DeepSeek-R1-Distill-Qwen-32B-Augmented-Responses

Viewer • Updated Mar 26 • 729 • 21

Sangsang/ContextualIntegritySyntheticDataset_DeepSeek-R1-Distill-Qwen-32B_all

Viewer • Updated Mar 26 • 729 • 23

Sangsang/ContextualIntegritySyntheticDataset_Olmo-3-7B-Think_all

Viewer • Updated Mar 26 • 729 • 39

Sangsang/ThinkSafe-R1-Distill-8B_unfiltered

Viewer • Updated Mar 26 • 40k • 12

Sangsang/ThinkSafe-Qwen3-8B_unfiltered

Viewer • Updated Mar 26 • 40k • 15

Sangsang/DeepSeek-R1-Distill-Qwen-14B-thinksafe

Viewer • Updated Mar 25 • 39.8k • 9

Sangsang/CI_v2_Qwen3-14B_all

Viewer • Updated Mar 25 • 729 • 6

Sangsang/CI_v2_Qwen3-4B_all

Viewer • Updated Mar 25 • 729 • 8

Sangsang/Qwen3-14B-thinksafe

Viewer • Updated Mar 25 • 40k • 8

Sangsang/test

Viewer • Updated Mar 25 • 100 • 7

Sangsang/CI_v2_DeepSeek-R1-Distill-Qwen-7B_disallowed

Viewer • Updated Mar 24 • 729 • 11

Sangsang/CI_v2_DeepSeek-R1-Distill-Llama-8B_disallowed

Viewer • Updated Mar 24 • 729 • 6

Sangsang/CI_v2_Qwen3-4B-Instruct-2507_disallowed

Viewer • Updated Mar 24 • 729 • 10

Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B-Instruct-2507_all

Viewer • Updated Mar 22 • 729 • 34

Sangsang/ContextualIntegritySyntheticDataset_DeepSeek-R1-Distill-Qwen-7B_all

Viewer • Updated Mar 20 • 729 • 20

Sangsang/ContextualIntegritySyntheticDataset_DeepSeek-R1-Distill-Llama-8B_all

Viewer • Updated Mar 20 • 729 • 41

Sangsang/ContextualIntegritySyntheticDataset_DeepSeek-R1-Distill-Llama-8B_disallowed

Viewer • Updated Mar 20 • 729 • 8

Sangsang/CI-Qwen2.5-7B-Instruct-Augmented-Responses

Viewer • Updated Mar 4 • 729 • 10