LRD framework with Frenet, NRS, and GFMI metrics shows layer-wise structure in 31 models provides usable signal for model selection and pruning on MTEB tasks.
Svcca: Singular vector canonical correlation analysis for deep learning dynamics and interpretability.Advances in neural information processing systems, 30
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.
citing papers explorer
-
Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs
LRD framework with Frenet, NRS, and GFMI metrics shows layer-wise structure in 31 models provides usable signal for model selection and pruning on MTEB tasks.
-
Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.