MCML - Research Blog

27.03.2025

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 …

Research at EWCS at the Broad Institute of MIT and Harvard

Cecilia Casolo - Funded by the MCML AI X-Change Program

During my research stay at Broad Institute of MIT and Harvard in autumn 2024, I had the pleasure of being part of the research group led by Caroline Uhler, Director of the Eric and Wendy Schmidt Center (EWCS) at the Broad Institute, and Andrew (1956) and Erna Viterbi Professor of Engineering in EECS and IDSS at MIT. My three-month stay in Boston …