A dataless regularizer based on Kronecker-Factored Approximate Curvature disentangles task vectors for improved task addition and negation in foundation models, with constant complexity and robustness to rescaling.
Results are reported forα= 1.0and the best-performingα
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
A dataless regularizer based on Kronecker-Factored Approximate Curvature disentangles task vectors for improved task addition and negation in foundation models, with constant complexity and robustness to rescaling.