A framework to identify and convert foldable layer normalizations to RMSNorm for exact equivalence and faster inference in deep neural networks.
and Lo, Wan-Yen and Dollar, Piotr and Girshick, Ross , title =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Depth Pro is a fast foundation model for zero-shot metric monocular depth estimation that produces sharp high-resolution depth maps with absolute scale using a multi-scale vision transformer.
citing papers explorer
-
Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm
A framework to identify and convert foldable layer normalizations to RMSNorm for exact equivalence and faster inference in deep neural networks.
-
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
Depth Pro is a fast foundation model for zero-shot metric monocular depth estimation that produces sharp high-resolution depth maps with absolute scale using a multi-scale vision transformer.