7 papers
Few-Shot Bioactivity Prediction with Meta-Learning under Assay Heterogeneity
Michal Kmicikiewicz, Tommy Rochussen, Vincent Fortuin +1
Accurate bioactivity prediction is a central challenge in early-stage drug discovery, as individual assays often contain too few measurements to train reliable models independently…
ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods
Michal Kmicikiewicz, Vincent Fortuin, Ewa Szczurek
Designing protein sequences of both high fitness and novelty is a challenging task in data-efficient protein engineering. Exploration beyond wild-type neighborhoods often leads to…
Can Transformers Learn Full Bayesian Inference in Context?
Arik Reuter, Tim G. J. Rudner, Vincent Fortuin +1
Transformers have emerged as the dominant architecture in the field of deep learning, with a broad range of applications and remarkable in-context learning (ICL) capabilities. Whil…
Stein Variational Newton Neural Network Ensembles
Klemens Flöge, Mohammed Abdul Moeed, Vincent Fortuin
Deep neural network ensembles are powerful tools for uncertainty quantification, which have recently been re-interpreted from a Bayesian perspective. However, current methods inade…
OneProt: Towards Multi-Modal Protein Foundation Models
Klemens Flöge, Srisruthi Udayakumar, Johanna Sommer +8
Recent advances in Artificial Intelligence have enabled multi-modal systems to model and translate diverse information spaces. Extending beyond text and vision, we introduce OnePro…
Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation
Richard D. Paul, Alessio Quercia, Vincent Fortuin +2
State-of-the-art computer vision tasks, like monocular depth estimation (MDE), rely heavily on large, modern Transformer-based architectures. However, their application in safety-c…