ZHENG JINGNAN

Nannanzi

5 1

·

AI & ML interests

None yet

Recent Activity

upvoted a collection about 10 hours ago

authored a paper 12 days ago

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI

authored a paper 12 days ago

Safin-1: Safety from Within through Memory-Native State Evolution

View all activity

Organizations

Nannanzi 's datasets 16

Nannanzi/evaluation_xstest_unsafe_safe

Viewer • Updated Mar 31, 2025 • 500 • 13

Nannanzi/evaluation_xstest_unsafe_unsafe

Viewer • Updated Mar 31, 2025 • 18 • 15

Nannanzi/evaluation_xstest_safe

Viewer • Updated Mar 31, 2025 • 500 • 28

Nannanzi/evaluation_jailbreak_unsafe

Viewer • Updated Mar 31, 2025 • 447 • 30

Nannanzi/evaluation_jailbreak_safe

Viewer • Updated Mar 31, 2025 • 500 • 25

Nannanzi/evaluation_plain_harmful_unsafe

Viewer • Updated Mar 31, 2025 • 500 • 9

Nannanzi/evaluation_plain_harmful_safe

Viewer • Updated Mar 31, 2025 • 500 • 15

Nannanzi/training_data_truncated

Viewer • Updated Mar 31, 2025 • 7.7k • 15

Nannanzi/processed_harmful_unharmful

Viewer • Updated Mar 31, 2025 • 79.5k • 11

Nannanzi/processed_harmful_harmful

Viewer • Updated Mar 31, 2025 • 84.7k • 36

Nannanzi/processed_alpaca_eval

Viewer • Updated Mar 31, 2025 • 52k • 14

Nannanzi/training_data

Viewer • Updated Mar 31, 2025 • 7.7k • 6

Nannanzi/cold_start

Viewer • Updated Mar 31, 2025 • 1.05k • 9

Nannanzi/evaluation_xstest_unsafe

Viewer • Updated Mar 30, 2025 • 600 • 8

Nannanzi/evaluation_jailbreak

Viewer • Updated Mar 30, 2025 • 500 • 18

Nannanzi/evaluation_plain_harmful

Viewer • Updated Mar 30, 2025 • 500 • 8