SBS improves NeRN weight compression by unidirectional kernel smoothing and RFF bandwidth that shrinks for larger networks, cutting required MLP parameters by roughly 2 to 3 times.
In: Pro- ceedings of the 36th International Conference on Machine Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
SBS improves NeRN weight compression by unidirectional kernel smoothing and RFF bandwidth that shrinks for larger networks, cutting required MLP parameters by roughly 2 to 3 times.