AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Efficient Plug-and-Play Weight Refinement for Sparse Large Models

Jingcheng Xie, Yinda Chen, Xiaoyu Liu, Yinglong Li, Haoyuan Shi, Zhiwei Xiong

AAAI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Layer-wise pruning of LLMs · 0 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
add EIWR refinementSparseGPT · WikiText2 LLaMA2-7B 70%perplexity: 23.5870 -> 20.2348Improved
add EIWR refinementWanda · WikiText2 LLaMA2-7B 70%perplexity: 73.0853 -> 22.9877Improved
add EIWR refinementWanda · WikiText2 Qwen2.5-3B 70%perplexity: 152.2175 -> 37.0856Improved
add PCG refinement instead of EIWRSparseGPT · WikiText2 LLaMA2-7B 70%perplexity: 23.5870 -> 21.9632Improved
add DSnoT refinementSparseGPT · WikiText2 LLaMA2-7B 70%perplexity: 23.5870 -> 67.5221Hurt
add DSnoT refinementWanda · WikiText2 LLaMA2-7B 70%perplexity: 73.0853 -> 72.9401No clear effect
add EIWR at 90% sparsitySparseGPT · WikiText2 LLaMA2-7B 90%perplexity: 1.32e3 -> 673.23Improved
add EIWR at 80% sparsitySparseGPT · WikiText2 LLaMA3-8B 80%perplexity: 176.42 -> 137.60Improved
add DSnoT on top of EIWR (ablation)EIWR · WikiText2 LLaMA2-7B 70%perplexity: 20.23 -> 19.73Improved
add AlphaPruning on top of EIWR (ablation)EIWR · WikiText2 LLaMA2-7B 70%perplexity: 20.23 -> 17.81Improved
use progressive instead of no momentum (ablation)EIWR · WikiText2 LLaMA2-7B 70%perplexity: 20.61 -> 16.47Improved
use progressive instead of fixed momentum (ablation)EIWR · WikiText2 LLaMA2-7B 70%perplexity: 18.95 -> 16.47Improved

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