Fairness benchmark for multimodal LLMs: dataset, image perturbations, and results (paper: Fairness Failure Modes of Multimodal LLMs).
AI & ML interests
None defined yet.
Recent Activity
datasets 12
MLL-Lab/MultiBBQ-results
Preview • Updated • 670
MLL-Lab/viewagent-ai2thor
Preview • Updated • 34
MLL-Lab/MultiBBQ
Viewer • Updated • 1.64k • 234
MLL-Lab/MultiBBQ-perturbations
Viewer • Updated • 8.59k • 4.67k
MLL-Lab/MultiBBQ-realworld
Viewer • Updated • 79 • 458
MLL-Lab/viewsuite
Updated • 270 • 1
MLL-Lab/BAGEN
Viewer • Updated • 445 • 180 • 3
MLL-Lab/MindTopo
Viewer • Updated • 8.91k • 115 • 2
MLL-Lab/Theory-of-Space
Viewer • Updated • 13.7k • 141 • 6
MLL-Lab/ENACT
Preview • Updated • 97 • 7