Weight Scope Alignment: A Frustratingly Easy Method for Model Merging

22 August 2024

Papers citing "Weight Scope Alignment: A Frustratingly Easy Method for Model Merging"

5 / 5 papers shown

Title
Plateau in Monotonic Linear Interpolation -- A "Biased" View of Loss Landscape for Deep Networks Xiang Wang Annie Wang Mo Zhou Rong Ge MoMe 158 10 0 03 Oct 2022
Git Re-Basin: Merging Models modulo Permutation Symmetries Samuel K. Ainsworth J. Hayase S. Srinivasa MoMe 239 312 0 11 Sep 2022
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications Andrew G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand M. Andreetto Hartwig Adam 3DH 948 20,471 0 17 Apr 2017
Aggregated Residual Transformations for Deep Neural Networks Saining Xie Ross B. Girshick Piotr Dollár Z. Tu Kaiming He 261 10,196 0 16 Nov 2016
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 273 2,878 0 15 Sep 2016