[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 a collection 1 day ago
Nemotron-Post-Training-v3 liked a dataset 5 days ago
nvidia/Nemotron-Personas-Korea upvoted an article 5 days ago
How to Ground a Korean AI Agent in Real Demographics with Synthetic PersonasOrganizations
None yet
datasets 7
oneonlee/SIUO
Viewer • Updated • 334 • 16
oneonlee/Meme-Safety-Bench
Viewer • Updated • 50.8k • 77 • 5
oneonlee/aegis2-train
Viewer • Updated • 30k • 41 • 1
oneonlee/wildguardmix-train
Viewer • Updated • 86.8k • 6
oneonlee/Wiki-NFQA
Viewer • Updated • 1.89k • 40 • 1
oneonlee/wiki-kg-prob
Viewer • Updated • 230 • 5
oneonlee/cleansed_emocontext
Viewer • Updated • 38.4k • 109 • 2