Sangwoo Park's picture

Sangwoo Park

Sangsang

·

swgger

AI & ML interests

I do LLM post-training research (KAIST AI)

Recent Activity

upvoted a paper 1 day ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

upvoted a paper 1 day ago

Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents

updated a model 2 days ago

Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen3-14B_bw0p5_fw0p5_ema0p999_ep30

View all activity

Organizations

None yet

Sangsang 's datasets 103

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

Viewer • Updated 7 days ago • 729 • 37

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

Viewer • Updated 7 days ago • 729 • 29

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

Viewer • Updated 7 days ago • 729 • 56

Sangsang/ContextualIntegritySyntheticDataset_Qwen3-32B_all

Viewer • Updated 9 days ago • 729 • 48

Sangsang/safepath_test_2

Viewer • Updated 20 days ago • 39.9k • 28

Sangsang/safepath_test

Viewer • Updated 20 days ago • 39.9k • 28

Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B_all

Viewer • Updated 20 days ago • 729 • 77

Sangsang/ContextualIntegritySyntheticDataset_Qwen3-8B_all

Viewer • Updated 20 days ago • 729 • 33

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

Viewer • Updated 21 days ago • 729 • 35

Sangsang/ContextualIntegritySyntheticDataset_Olmo-3-32B-Think_all

Viewer • Updated 21 days ago • 729 • 35

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

Viewer • Updated 21 days ago • 40k • 34

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

Viewer • Updated 22 days ago • 40k • 60

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

Viewer • Updated 22 days ago • 729 • 37

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

Viewer • Updated 22 days ago • 729 • 35

Sangsang/ContextualIntegritySyntheticDataset_Olmo-3-7B-Think_all

Viewer • Updated 22 days ago • 729 • 68

Sangsang/ThinkSafe-R1-Distill-8B_unfiltered

Viewer • Updated 22 days ago • 40k • 22

Sangsang/ThinkSafe-Qwen3-8B_unfiltered

Viewer • Updated 22 days ago • 40k • 24

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

Viewer • Updated 23 days ago • 39.8k • 28

Sangsang/CI_v2_Qwen3-14B_all

Viewer • Updated 23 days ago • 729 • 25

Sangsang/CI_v2_Qwen3-4B_all

Viewer • Updated 23 days ago • 729 • 29

Sangsang/Qwen3-14B-thinksafe

Viewer • Updated 23 days ago • 40k • 26

Sangsang/test

Viewer • Updated 23 days ago • 100 • 26

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

Viewer • Updated 24 days ago • 729 • 28

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

Viewer • Updated 24 days ago • 729 • 27

Sangsang/CI_v2_Qwen3-4B-Instruct-2507_disallowed

Viewer • Updated 24 days ago • 729 • 25

Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B-Instruct-2507_all

Viewer • Updated 26 days ago • 729 • 52

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

Viewer • Updated 28 days ago • 729 • 40

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

Viewer • Updated 28 days ago • 729 • 50

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

Viewer • Updated 28 days ago • 729 • 19

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

Viewer • Updated Mar 4 • 729 • 16