linear mode connectivity
PulseAugur coverage of linear mode connectivity — every cluster mentioning linear mode connectivity across labs, papers, and developer communities, ranked by signal.
-
New framework enables linear merging of billion-parameter transformers
Researchers have developed a new framework for merging large pretrained transformers, specifically those with billions of parameters. This method addresses limitations of previous approaches by optimizing interpolation …
-
Deep Ensembles Show Linear Mode Connectivity Under Data Shifts
Researchers have investigated the phenomenon of linear mode connectivity (LMC) in deep learning, particularly how it is affected by data shifts in ensembles of image classifiers. The study suggests that data shifts can …
-
New research explores merging large transformers and improving looped model stability
Two new research papers explore novel techniques for enhancing the capabilities and stability of large transformer models. The first paper introduces a scalable framework for linear mode connectivity (LMC) that allows f…
-
New theory explores linear mode connectivity via neuron identifiability
Researchers have developed a new theoretical framework to understand linear mode connectivity in deep learning, focusing on neuron identifiability. This approach reveals that neural networks can possess multiple equival…