🏢 University of Copenhagen

LoQT enables efficient large language model training on consumer hardware via quantized weights and low-rank weight updates, overcoming memory limitations.

Kermut: A novel Gaussian process regression model achieves state-of-the-art accuracy in predicting protein variant effects and provides reliable uncertainty estimates, crucial for protein engineering …

New framework uses rough path theory to enable gradient-based training of SSNNs driven by rough signals, allowing for noise in spike timing and network dynamics.

Conditioning infinite-dimensional nonlinear diffusion processes is made possible, enabling analysis of complex data like organism shapes in evolutionary biology.

BMRS: Bayesian Model Reduction for Structured Pruning offers a principled, threshold-free approach to neural network compression, achieving high accuracy and competitive efficiency.