14 citations · 16 across the 2 of their papers we have counts for
2 papers
cs.CV2024★ 2 cited
Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks
Maan Qraitem, Nazia Tasnim, Piotr Teterwak +2
Typographic attacks, adding misleading text to images, can deceive vision-language models (LVLMs). The susceptibility of recent large LVLMs like GPT4-V to such attacks is understud…
cs.CV2022★ 14 cited
Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark
Vitali Petsiuk, Alexander E. Siemenn, Saisamrit Surbehera +11
We provide a new multi-task benchmark for evaluating text-to-image models. We perform a human evaluation comparing the most common open-source (Stable Diffusion) and commercial (DA…