5 papers
QMaxCal: Path-Space Regularization for Open Quantum Control via Girsanov's Theorem
Merijn Moody, Zier Mensch, Miranda C. N. Cheng +2
Reliable quantum control in the presence of decoherence requires policies that combat the effect of environmental noise on the controlled dynamics. Open quantum systems under conti…
Discovering and decoding latent mean-field structure with variational autoencoders
Marco Biroli, Max Welling, Vincenzo Vitelli
Generative models are increasingly used to capture correlations in many-body systems, but the representations they learn remain largely opaque to physical interpretation. Here, we…
BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models
Dario Coscia, Sindy Löwe, Max Welling
Low-Rank Adaptation (LoRA) has become the standard for fine-tuning large pre-trained models at reduced computational cost. However, its low-rank point-estimate updates limit expres…
BLIPs: Bayesian Learned Interatomic Potentials
Dario Coscia, Pim de Haan, Max Welling
Machine Learning Interatomic Potentials (MLIPs) are becoming a central tool in simulation-based chemistry. However, like most deep learning models, MLIPs struggle to make accurate…
BARNN: A Bayesian Autoregressive and Recurrent Neural Network
Dario Coscia, Max Welling, Nicola Demo +1
Autoregressive and recurrent networks have achieved remarkable progress across various fields, from weather forecasting to molecular generation and Large Language Models. Despite t…