PKU-Alignment/Deception_sandbox
Updated
AI & ML interests
Reinforcement Learning, Large Language Models, Value Alignment
Recent Activity
View all activity
PKU-Alignment/InterMT
Preview • Updated • 212
PKU-Alignment/VLA-Arena-Scenes
Updated • 44 • 1
PKU-Alignment/TruthfulVQA-image
Viewer • Updated • 5.1k • 59 • 1
PKU-Alignment/TruthfulVQA-text
Viewer • Updated • 15.3k • 18
PKU-Alignment/self-monitor
Viewer • Updated • 11.3k • 19
PKU-Alignment/DeceptionBench
Viewer • Updated • 180 • 401 • 3
PKU-Alignment/LatentJailbreak
Viewer • Updated • 416 • 18
PKU-Alignment/InterMT-Bench-Images
Viewer • Updated • 1.51k • 5
PKU-Alignment/TruthfulVQA
Viewer • Updated • 15.3k • 29 • 4
PKU-Alignment/align-anything
Viewer • Updated • 69.4k • 1.82k • 47
PKU-Alignment/PKU-SafeRLHF-V
Viewer • Updated • 30.4k • 225 • 6
PKU-Alignment/BeaverTails-V
Viewer • Updated • 60.8k • 364 • 3
PKU-Alignment/s1-m_beta
Viewer • Updated • 14.6k • 18
PKU-Alignment/Flames-1k-Chinese
Viewer • Updated • 2k • 30 • 1
PKU-Alignment/DollyTails-12K
Viewer • Updated • 11.8k • 7 • 7
PKU-Alignment/EvalAnything-InstructionFollowing
Viewer • Updated • 6.7k • 57
PKU-Alignment/EvalAnything-Selection_Synergy
Viewer • Updated • 100 • 52
PKU-Alignment/EvalAnything-AMU
Updated • 65
PKU-Alignment/Align-Anything-TI2T-Instruction-100K
Viewer • Updated • 103k • 144 • 1
PKU-Alignment/PKU-SafeRLHF
Viewer • Updated • 164k • 15.1k • 179
PKU-Alignment/Align-Anything-Instruction-100K-zh
Viewer • Updated • 105k • 110 • 10
PKU-Alignment/Align-Anything-Instruction-100K
Viewer • Updated • 105k • 127 • 9
PKU-Alignment/MVBench
Viewer • Updated • 4k • 102
PKU-Alignment/MM-SafetyBench
Viewer • Updated • 6.72k • 3.04k • 6
PKU-Alignment/SafeSora-Prompt
Viewer • Updated • 36.6k • 5
PKU-Alignment/ProgressGym-TimelessQA
Preview • Updated • 64 • 1
PKU-Alignment/ProgressGym-MoralEvals
Preview • Updated • 111 • 3
PKU-Alignment/ProgressGym-HistText
Preview • Updated • 138 • 1
PKU-Alignment/SafeSora-Label
Viewer • Updated • 57.3k • 55 • 2