pith. sign in

Beyond task vectors: Selective task arithmetic based on importance metrics

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 2

years

2026 1 2025 1

verdicts

UNVERDICTED 2

representative citing papers

AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise

cs.AI · 2026-05-31 · unverdicted · novelty 6.0

AnyEdit++ proposes Bayes-Chunk, an adaptive segmentation method based on Bayesian Surprise, with theoretical claims of structural independence and causal locality, reporting superior results over baselines on math, code, and narrative tasks.

Model Merging Scaling Laws in Large Language Models

cs.AI · 2025-09-29 · unverdicted · novelty 6.0

Empirical scaling laws for LLM merging show a size-dependent floor and 1/k-like tail in cross-entropy loss that holds across architectures and merging methods.

citing papers explorer

Showing 2 of 2 citing papers.

  • AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise cs.AI · 2026-05-31 · unverdicted · none · ref 38

    AnyEdit++ proposes Bayes-Chunk, an adaptive segmentation method based on Bayesian Surprise, with theoretical claims of structural independence and causal locality, reporting superior results over baselines on math, code, and narrative tasks.

  • Model Merging Scaling Laws in Large Language Models cs.AI · 2025-09-29 · unverdicted · none · ref 2

    Empirical scaling laws for LLM merging show a size-dependent floor and 1/k-like tail in cross-entropy loss that holds across architectures and merging methods.