Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Grokking Explained: A Statistical Phenomenon
Breno W. Carvalho, Artur S. d'Avila Garcez, LuÃs C. Lamb +1
Grokking, or delayed generalization, is an intriguing learning phenomenon where test set loss decreases sharply only after a model's training set loss has converged. This challenge…
cs.LG2024
A Large Encoder-Decoder Family of Foundation Models For Chemical Language
Eduardo Soares, Victor Shirasuna, Emilio Vital Brazil +3
Large-scale pre-training methodologies for chemical language models represent a breakthrough in cheminformatics. These methods excel in tasks such as property prediction and molecu…