[EMNLP'25] A Benchmark for Assessing VLM Safety with Real-World Memes
DongGeon Lee
oneonlee
AI & ML interests
Data-centric natural language processing, AI Safety & Alignment
Recent Activity
authored a paper about 10 hours ago
Multimodal Safety Evaluation Should Measure Controllability Beyond Classification liked a dataset 2 months ago
yczhuang/Hephaestus-Forge liked a dataset 2 months ago
jumplander/JL-Agentic-Behavior-10KOrganizations
datasets 7
oneonlee/SIUO
Viewer • Updated • 334 • 25
oneonlee/Meme-Safety-Bench
Viewer • Updated • 50.8k • 248 • 7
oneonlee/aegis2-train
Viewer • Updated • 30k • 14 • 1
oneonlee/wildguardmix-train
Viewer • Updated • 86.8k • 23
oneonlee/Wiki-NFQA
Viewer • Updated • 1.89k • 16 • 1
oneonlee/wiki-kg-prob
Viewer • Updated • 230 • 4
oneonlee/cleansed_emocontext
Viewer • Updated • 38.4k • 235 • 2