pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

SimDiff: Depth Pruning via Similarity and Difference

cs.AI · 2026-04-21 · unverdicted · novelty 7.0

SimDiff uses similarity and difference metrics to prune LLM layers more effectively than cosine similarity alone, retaining over 91% performance at 25% pruning on LLaMA2-7B.

citing papers explorer

Showing 1 of 1 citing paper.

  • SimDiff: Depth Pruning via Similarity and Difference cs.AI · 2026-04-21 · unverdicted · none · ref 9

    SimDiff uses similarity and difference metrics to prune LLM layers more effectively than cosine similarity alone, retaining over 91% performance at 25% pruning on LLaMA2-7B.