[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
liked a dataset about 18 hours ago
nvidia/Nemotron-Personas-Korea upvoted an article about 18 hours ago
How to Ground a Korean AI Agent in Real Demographics with Synthetic Personas liked a dataset 8 days ago
huggingface-KREW/Ko-AgentBenchOrganizations
None yet
datasets 7
oneonlee/SIUO
Viewer • Updated • 334 • 15
oneonlee/Meme-Safety-Bench
Viewer • Updated • 50.8k • 67 • 5
oneonlee/aegis2-train
Viewer • Updated • 30k • 42 • 1
oneonlee/wildguardmix-train
Viewer • Updated • 86.8k • 8
oneonlee/Wiki-NFQA
Viewer • Updated • 1.89k • 36 • 1
oneonlee/wiki-kg-prob
Viewer • Updated • 230 • 3
oneonlee/cleansed_emocontext
Viewer • Updated • 38.4k • 34 • 2