Munich Center for Machine Learning

Retrofitting language models to operate over bytes

Abstract Recent advances in artificial intelligence (AI) have largely been driven by large language models, deep neural networks that operate over discrete units called tokens. To represent text, most large language models use words or word fragments as the tokens, known as subwo...

Prediction-Based Adaptive Designs for Reducing Wave Nonresponse Rates and Bias in Panel Surveys

Machine learning (ML)-based nonresponse prediction in panel surveys enables selective interventions. However, the optimal use of ML predictions in Adaptive Survey Design (ASD) remains uncertain. We propose a method that integrates field experiment results on incentives, questionn...

Conditional deep generative modeling of blood-based infrared spectra enables controlled in-silico phenotyping studies

Abstract Infrared molecular fingerprinting of blood offers a scalable, minimally invasive window into human physiology, but limited follow-up, imbalanced cohorts, and restricted access to diverse phenotypes constrain systematic studies. Here, we introduce a conditional deep gener...

Quantum circuit-based learning models: bridging quantum computing and machine learning

Abstract Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophistic...

Tracking funding disparities in global health aid with machine learning

Abstract Reducing the global burden of disease is crucial for improving health outcomes. However, misalignment between health aid and country-level disease burden leaves vulnerable populations without the necessary support for major health challenges, particularly in the least de...

CODAC: Constraint-based Deep Active Clustering

Abstract Constraint-based Deep Active Clustering (CODAC) integrates actively selected pairwise constraints into deep representation learning to efficiently improve existing cluster structures, even under tight query budgets. CODAC encodes the constraint information into the embed...