In deep learning theory, the covariance matrix of the representations se...
Autoregressive Transformers adopted in Large Language Models (LLMs) are ...
In contrast to the natural capabilities of humans to learn new tasks in ...
Despite the empirical advances of deep learning across a variety of lear...
Transformers have achieved remarkable success in several domains, rangin...
While Bayesian neural networks (BNNs) provide a sound and principled
alt...
Recent works on Bayesian neural networks (BNNs) have highlighted the nee...
The "cold posterior effect" (CPE) in Bayesian deep learning describes th...
Knowledge Graphs (KG) are gaining increasing attention in both academia ...