2 papers
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.CE2024
SELF-BART : A Transformer-based Molecular Representation Model using SELFIES
Indra Priyadarsini, Seiji Takeda, Lisa Hamada +3
Large-scale molecular representation methods have revolutionized applications in material science, such as drug discovery, chemical modeling, and material design. With the rise of…