5 papers
Unlocking UML Class Diagram Understanding in Vision Language Models
Artem Naboichenko, René Peinl
Although Vision Language Models (VLMs) have seen tremendous progress across all kinds of use cases, they still fall behind in answering questions regard-ing diagrams compared to ph…
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…
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…
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…