AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

D2 Prune: Sparsifying Large Language Models via Dual Taylor Expansion and Attention Distribution Awareness

Lang Xiong, Ning Liu, Ao Ren, Yuheng Bai, Haining Fang, Binyan Zhang, Zhe Jiang, Yujuan Tan, Duo Liu

AAAI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Layer-wise pruning of LLMs · 3 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 dual Taylor activation terms (ablation)SparseGPT · LLaMA-3-8B WikiText2, 50-80% sparsityperplexity: 8.56 -> 8.48 (50%); 178.01 -> 170.92 (80%)Improved
add dual Taylor activation terms (ablation)Wanda · LLaMA-3-8B WikiText2, 50-80% sparsityperplexity: 2245.91 -> 1414.32 (80%)Improved
update q, k, v in all attention layers instead of none (ablation)D2Prune · LLaMA-2-7B WikiText2, 70%perplexity: 81.62 -> 23.45Improved
leave v un-updated while updating q and k (dynamic update) (ablation)D2Prune · LLaMA-2-7B WikiText2, 70%perplexity: 23.45 -> 21.10Improved
leave q or k un-updated instead of v (ablation)D2Prune · LLaMA-2-7B WikiText2, 70%perplexity: 21.10 -> 25.16 (q), 24.04 (k)Hurt
update all q/k/v at 80% sparsity vs dynamic (ablation)D2Prune · LLaMA-2-7B WikiText2, 80%perplexity: 101.88 -> 92.68Improved
add LoRA fine-tuning to pruned model (ablation)D2Prune · LLaMA-2-7B WikiText2, 70%perplexity: 21.10 -> 9.70Improved
use optimal q/k/v update configuration across sparsity levels (ablation)D2Prune · LLaMA-2-7BperplexityNo clear effect
D2Prune versus SparseGPT at 50% on LLaMA-2-7BD2Prune · LLaMA-2-7B WikiText2, 50%perplexity: 6.52 -> 6.36Improved
D2Prune versus Pruner-Zero at 50%, zero-shotD2Prune · LLaMA-2-7B, 50%accuracy: 59.26 -> 61.06Improved
D2Prune versus Wanda at 50% (small gap)D2Prune · LLaMA-2-7B WikiText2, 50%perplexity: 6.44 -> 6.36No clear effect

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