PKU-Alignment

university

https://github.com/PKU-Alignment

AI & ML interests

Reinforcement Learning, Large Language Models, Value Alignment

Recent Activity

alignmentforever updated a dataset 8 days ago

PKU-Alignment/InterMT

muchvo published a dataset about 1 month ago

PKU-Alignment/VLA-Arena-Scenes

XuehaiPan authored a paper about 1 month ago

AI Alignment: A Comprehensive Survey

View all activity

PKU-Alignment 's datasets 40

PKU-Alignment/InterMT

Preview • Updated 8 days ago • 213

PKU-Alignment/VLA-Arena-Scenes

Updated Dec 15, 2025 • 37 • 1

PKU-Alignment/TruthfulVQA-image

Viewer • Updated Jul 25, 2025 • 5.1k • 35 • 1

PKU-Alignment/TruthfulVQA-text

Viewer • Updated Jul 24, 2025 • 15.3k • 10

PKU-Alignment/self-monitor

Viewer • Updated Jul 9, 2025 • 11.3k • 24

PKU-Alignment/DeceptionBench

Viewer • Updated May 27, 2025 • 180 • 275 • 2

PKU-Alignment/LatentJailbreak

Viewer • Updated May 24, 2025 • 416 • 23

PKU-Alignment/InterMT-Bench-Images

Viewer • Updated May 23, 2025 • 1.51k • 11

PKU-Alignment/TruthfulVQA

Viewer • Updated May 15, 2025 • 15.3k • 67 • 3

PKU-Alignment/align-anything

Viewer • Updated Apr 5, 2025 • 69.4k • 3.02k • 47

PKU-Alignment/PKU-SafeRLHF-V

Viewer • Updated Mar 25, 2025 • 30.4k • 124 • 5

PKU-Alignment/BeaverTails-V

Viewer • Updated Mar 25, 2025 • 60.8k • 205 • 2

PKU-Alignment/s1-m_beta

Viewer • Updated Mar 15, 2025 • 14.6k • 15

PKU-Alignment/Flames-1k-Chinese

Viewer • Updated Feb 7, 2025 • 2k • 50 • 1

PKU-Alignment/DollyTails-12K

Viewer • Updated Jan 17, 2025 • 11.8k • 57 • 7

PKU-Alignment/EvalAnything-InstructionFollowing

Viewer • Updated Dec 28, 2024 • 6.7k • 72

PKU-Alignment/EvalAnything-Selection_Synergy

Viewer • Updated Dec 28, 2024 • 100 • 50

PKU-Alignment/EvalAnything-AMU

Updated Dec 28, 2024 • 156

PKU-Alignment/Align-Anything-TI2T-Instruction-100K

Viewer • Updated Nov 20, 2024 • 103k • 193 • 1

PKU-Alignment/PKU-SafeRLHF

Viewer • Updated Oct 18, 2024 • 164k • 6.47k • 170

PKU-Alignment/Align-Anything-Instruction-100K-zh

Viewer • Updated Oct 10, 2024 • 105k • 92 • 8

PKU-Alignment/Align-Anything-Instruction-100K

Viewer • Updated Oct 10, 2024 • 105k • 85 • 9

PKU-Alignment/MVBench

Viewer • Updated Oct 4, 2024 • 4k • 193

PKU-Alignment/MM-SafetyBench

Viewer • Updated Sep 19, 2024 • 6.72k • 923 • 3

PKU-Alignment/SafeSora-Prompt

Viewer • Updated Aug 12, 2024 • 36.6k • 26

PKU-Alignment/ProgressGym-TimelessQA

Preview • Updated Aug 10, 2024 • 77 • 1

PKU-Alignment/ProgressGym-MoralEvals

Preview • Updated Aug 10, 2024 • 62 • 3

PKU-Alignment/ProgressGym-HistText

Preview • Updated Aug 10, 2024 • 1.57k • 1

PKU-Alignment/SafeSora-Label

Viewer • Updated Jun 20, 2024 • 57.3k • 25 • 2

PKU-Alignment/SafeSora-Eval

Viewer • Updated Jun 20, 2024 • 600 • 24 • 2