[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
upvoted an article about 15 hours ago
Security incident disclosure — July 2026 liked a dataset 12 days ago
K-intelligence/KSAFE-MM liked a dataset 14 days ago
prometheus-eval/k-browsecompOrganizations
None yet
datasets 7
oneonlee/SIUO
Viewer • Updated • 334 • 30
oneonlee/Meme-Safety-Bench
Viewer • Updated • 50.8k • 68 • 6
oneonlee/aegis2-train
Viewer • Updated • 30k • 14 • 1
oneonlee/wildguardmix-train
Viewer • Updated • 86.8k • 9
oneonlee/Wiki-NFQA
Viewer • Updated • 1.89k • 13 • 1
oneonlee/wiki-kg-prob
Viewer • Updated • 230 • 11
oneonlee/cleansed_emocontext
Viewer • Updated • 38.4k • 257 • 2