MCML - Research Blog

03.04.2025

CUPS: Teaching AI to Understand Scenes Without Human Labels

MCML Research Insight - With Christoph Reich, Nikita Araslanov, and Daniel Cremers

What matters now

Understanding the location and semantics of objects in a scene is a significant task, enabling robots to navigate through complex environments or facilitating autonomous driving. Recent AI models for understanding scenes from images require significant guidance from humans in the …

Beyond the Black Box: Choosing the Right Feature Importance Method

MCML Research Insight - With Fiona Katharina Ewald, Ludwig Bothmann, Giuseppe Casalicchio and Bernd Bischl

Machine learning models make powerful predictions, but can we really trust them if we don’t understand how they work? Global feature importance methods help us discover which factors really matter - but choosing the wrong method can lead to misleading conclusions. To see why this is important, consider a real-world example from medicine.

ReNO: A Smarter Way to Enhance AI-Generated Images

MCML Research Insight - With Luca Eyring, Shyamgopal Karthik, Karsten Roth and Zeynep Akata

Despite their impressive capabilities, Text-to-Image (T2I) models frequently misinterpret detailed prompts, leading to errors in object positioning, attribute accuracy, and color fidelity. Traditional improvements rely on extensive dataset training, which is not only computationally expensive but also may not generalize well to unseen prompts. To …