Robot Holmes and the Vision-Language Murder Mysteries PyData London 2023

Join the detective **Robot Holmes** on an adventure through the streets of the vibrant city of **MLington**. Together, we will find out who is behind a series of mysterious murders in the bustling neighbourhood of **Vision-Language Village** (ViLaVi). ViLaVi has seen a steady influx of new posh Vision-Language models, which are not only rapidly expanding the size of the district but also the quality of services that are offered in these streets. On his journey Robot Holmes will compile an overview of the tasks these new models excel in and find out what makes them so good at it. Additionally he will gather details on some of the most successful of the Vision-Language models and eventually find out who or what is behind the series of murders. By the end of our journey you will have a better overview of the rapidly expanding Vision-Language neighbourhood and will have knowledge of the most important inner workings of Vision-Language models like **CLIP**, **OWL-ViT**, and **BLIP**. You will also know how to run them yourself in a few lines of code with the **transformers library** by Hugging Face. The talk is for everyone interested in the topic of **Vision-Language models** and who wants to gain some first insights into their ways of working. People who already have a profound knowledge of Vision-Language models are welcome as well, as they probably have never seen it presented as a crime story in a strangely familiar city.