The paper introduces Geometry, Resource, and Domino models that reproduce the sequential Domino effect in skill learning and link it to scaling laws, optimizers, and modularity.
Task arithmetic in the tangent space: Improved editing of pre-trained models
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
-
Physics of Skill Learning
The paper introduces Geometry, Resource, and Domino models that reproduce the sequential Domino effect in skill learning and link it to scaling laws, optimizers, and modularity.