AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization

Lawrence Liu, Alexander Liu, Mengdi Wang, Tuo Zhao, Lin F. Yang

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Layer-wise pruning of LLMs · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
wrap 2:4 sparse core with block-diagonal matrices and optimize by block coordinate descent (ARMOR vs NoWag-P init) (ablation)NoWag-P 2:4 · GSM8K Qwen2.5-7Baccuracy (%): 28.28 -> 53.28Improved
ARMOR vs NoWag-P (ablation)NoWag-P 2:4 · MMLU Qwen2.5-7Baccuracy (%): 53.51 -> 65.56Improved
ARMOR vs NoWag-P (ablation)NoWag-P 2:4 · Wikitext2 Llama-2-13Bperplexity: 8.28 -> 6.37Improved
ARMOR vs NoWag-P (ablation)NoWag-P 2:4 · Wikitext2 Llama-3-8Bperplexity: 24.0 -> 10.10Improved
ARMOR on 2:4 Qwen2.5-32B GPQA vs denseARMOR · GPQA Qwen2.5-32Baccuracy (%): 30.36 (SparseGPT) -> 39.51 (dense 38.84)Improved
apply ARMOR to other sparsity patterns (4:8, 5:8, 6:8, 50% unstructured)NoWag-P · Wikitext2 Llama-2-7Bperplexity: 4:8: 8.04 -> 6.74; 50%: 6.37 -> 6.13Improved
increase block diagonal block size from 1 to 128 (ablation)ARMOR · C4 perplexity Llama-2/3relative perplexityImproved
minimize proxy loss longer (more optimization iterations) (ablation)ARMOR · C4 perplexity Llama-2-7BperplexityImproved
ARMOR vs SparseGPT+DenoiseRotator at context 2048ARMOR · Wikitext2 Llama-3-8Bperplexity: 10.01 -> 11.27Hurt
ARMOR block-diagonal wrappers vs naive 2:4 inferencenaive 2:4 · generation throughput Qwen2.5-7Btokens/s: 5430 -> 5090Hurt

Later papers that compared with this method

1 later accepted paper reports ARMOR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy