Sangwoo Park

Sangsang

·

AI & ML interests

I do LLM post-training & Distillation research (KAIST AI)

Recent Activity

upvoted a paper 4 days ago

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

upvoted a paper 4 days ago

EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

upvoted a paper 5 days ago

Follow the Entities: A Corpus Map for Agentic Search

View all activity

Organizations

None yet

Sangsang 's datasets 111

Sangsang/thinksafe-r1-distill-8B-n5-filtered-all

Viewer • Updated Nov 17, 2025 • 191k • 12

Sangsang/thinksafe-8B-n5-filtered-all

Viewer • Updated Nov 17, 2025 • 197k • 24

Sangsang/thinksafe-r1-distill-7B-n5_filtered_all

Viewer • Updated Nov 17, 2025 • 216k • 6

Sangsang/thinksafe-4B-n5-filtered-all

Viewer • Updated Nov 17, 2025 • 194k • 40

Sangsang/thinksafe-1.7B-n5_filtered_all

Viewer • Updated Nov 17, 2025 • 176k • 2

Sangsang/thinksafe-0.6B-n5_filtered_all

Viewer • Updated Nov 17, 2025 • 181k • 2

Sangsang/thinksafe-r1-distill-1.5B-n5_filtered_all

Viewer • Updated Nov 17, 2025 • 173k • 3

Sangsang/ThinkSafe-R1-Distill-1.5B-n5_math-n5-t3_8k

Viewer • Updated Nov 11, 2025 • 195k • 43

Sangsang/ThinkSafe-R1-Distill-8B-n5_math-n5-t3_8k

Viewer • Updated Nov 11, 2025 • 201k • 59

Sangsang/ThinkSafe-R1-Distill-8B-n5_math-n5-t3_16k

Viewer • Updated Nov 11, 2025 • 201k • 43

Sangsang/thinksafe_r1-distill_1.5B_assisted

Viewer • Updated Nov 1, 2025 • 38.3k • 4

Sangsang/thinksafe_r1-distill_7B_assisted

Viewer • Updated Nov 1, 2025 • 39.2k • 3

Sangsang/gpt-oss-safeguard-20b_rationale

Viewer • Updated Nov 1, 2025 • 17.9k • 2

Sangsang/thinksafe_r1-distill_1.5B_debug

Viewer • Updated Oct 13, 2025 • 965

Sangsang/MobileLLM-R1-140M-base_thinksafe

Viewer • Updated Sep 21, 2025 • 869 • 5

Sangsang/MobileLLM-R1-950M_thinksafe

Viewer • Updated Sep 21, 2025 • 35.1k • 7

Sangsang/MobileLLM-R1-360M_thinksafe

Viewer • Updated Sep 21, 2025 • 29.7k • 3

Sangsang/MobileLLM-R1-140M_thinksafe

Viewer • Updated Sep 20, 2025 • 22.6k • 11

Sangsang/OpenThoughts-80K-8B

Updated Sep 17, 2025 • 2

Sangsang/OpenThoughts-80K-4B

Updated Sep 17, 2025 • 3

Sangsang/ThinkSafe

Viewer • Updated Sep 11, 2025 • 39k • 1