In the context of few-shot learning, it is currently believed that a fix...
Current trends to pre-train capable Large Language Models (LLMs) mostly ...
Recent work claims that large language models display emergent abilities...
Despite a growing body of work at the intersection of deep learning and
...
Recently, it has been observed that a transfer learning solution might b...
Recent work has suggested that a good embedding is all we need to solve ...
Recently, it has been observed that a transfer learning solution might b...
We review recent observations on the dynamical systems induced by gradie...
Given two networks with the same training loss on a dataset, when would ...
A main puzzle of deep neural networks (DNNs) revolves around the apparen...
In Theory IIb we characterize with a mix of theory and experiments the
o...
A main puzzle of deep networks revolves around the absence of overfittin...