Pith. sign in

Extreme compression of large language models via additive quantization

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Symmetric Pruning of Large Language Models

cs.LG · 2025-01-31 · conditional · novelty 4.0

SymWanda expresses Wanda and RIA pruning scores as special cases of a symmetric input-output reconstruction objective, and R2-DSnoT adds modest training-free post-pruning gains.

citing papers explorer

Showing 1 of 1 citing paper.

  • Symmetric Pruning of Large Language Models cs.LG · 2025-01-31 · conditional · none · ref 6

    SymWanda expresses Wanda and RIA pruning scores as special cases of a symmetric input-output reconstruction objective, and R2-DSnoT adds modest training-free post-pruning gains.