Scientists design molecules 'backward' to speed up discovery

Every medication in your cabinet, every material in your phone's battery, and virtually every compound that makes modern life work started as a molecular guess, with scientists hypothesizing that a ...
IEEE

Matrix-Inversion-Free Sparse Bayesian Learning for High-Resolution Radar Imagery via Improved Variational Inference

Abstract: Sparse Bayesian learning (SBL) is an advanced statistical framework that dominantly enhances the sparse features of targets of interest in radar imagery. A widely adopted strategy for ...
Helsinki

Theoretical and Computational Methods | Master's programme

The basis of natural sciences is the modelling of phenomena and solving the resulting models. The Master’s Programme in Theoretical and Computational Methods will give you a strong basis in the ...
IEEE

Multi-View Fused Nonnegative Matrix Completion Methods for Drug-Target Interaction Prediction

Abstract: Accurate prediction of drug-target interactions (DTIs) is crucial for accelerating drug discovery and reducing experimental costs. However, challenges such as sparse interactions and ...
GitHub

ADFT: Adapter-based Dual-branch Fine-Tuning for Fully Few-Shot Class-Incremental Audio Classification

This is the official repository for the paper "Generalization and Adaptation for Pre-trained Model-based Fully Few-Shot Class-Incremental Audio Classification" submitted to ICASSP 2026. Fully Few-shot ...