4 papers
SITUATE -- Synthetic Object Counting Dataset for VLM training
René Peinl, Vincent Tischler, Patrick Schröder +1
We present SITUATE, a novel dataset designed for training and evaluating Vision Language Models on counting tasks with spatial constraints. The dataset bridges the gap between simp…
VLM@school -- Evaluation of AI image understanding on German middle school knowledge
René Peinl, Vincent Tischler
This paper introduces a novel benchmark dataset designed to evaluate the capabilities of Vision Language Models (VLMs) on tasks that combine visual reasoning with subject-specific…
Using LLMs as prompt modifier to avoid biases in AI image generators
René Peinl
This study examines how Large Language Models (LLMs) can reduce biases in text-to-image generation systems by modifying user prompts. We define bias as a model's unfair deviation f…
Benchmarking Vision Language Models on German Factual Data
René Peinl, Vincent Tischler
Similar to LLMs, the development of vision language models is mainly driven by English datasets and models trained in English and Chinese language, whereas support for other langua…