wang's picture

1 9

wang

xinpeng

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

Refusal Direction is Universal Across Safety-Aligned Languages

updated a dataset about 2 months ago

xinpeng/Big-Math-RL-Verified-Combined-digit-hard-int-only

published a dataset about 2 months ago

xinpeng/Big-Math-RL-Verified-Combined-digit-hard-int-only

View all activity

Organizations

models 0

None public yet

datasets 14

xinpeng/Big-Math-RL-Verified-Combined-digit-hard-int-only

Viewer • Updated Apr 10 • 25.8k • 35

xinpeng/Big-Math-RL-Verified-Combined-digit-hard

Viewer • Updated Mar 31 • 25.9k • 42

xinpeng/Big-Math-RL-Verified-Combined-digit

Viewer • Updated Mar 31 • 130k • 29

xinpeng/sycophancy_separate_long_cot_simple

Viewer • Updated Mar 19 • 10.2k • 26

xinpeng/sycophancy_separate_cot_simple

Viewer • Updated Mar 19 • 10.2k • 26

xinpeng/sycophancy_separate_10x_long_cot

Viewer • Updated Mar 17 • 10.2k • 29

xinpeng/sycophancy_separate_long_cot

Viewer • Updated Mar 16 • 10.2k • 26

xinpeng/sycophancy_separate_cot

Viewer • Updated Mar 15 • 10.2k • 35

xinpeng/sycophancy_separate

Viewer • Updated Mar 4 • 10.2k • 23

xinpeng/sycophancy

Viewer • Updated Feb 22 • 10.2k • 18