AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

PosPrune: Visual Token Pruning with Positional Bias Correction for Efficient Large Vision-Language Models

Ziyang Wang, Mengwei Li, Hao Yin, Wenhao Liu, Zilei Wang

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Attention-based visual token pruning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes PosPrune, a visual token pruning method for LVLMs that corrects positional bias in token selection to reduce computation.

Problem

Large numbers of visual tokens from vision encoders add substantial computational overhead to large vision-language models; existing pruning methods rely on [CLS]-based attention in the vision encoder or prune inside LLM decoding layers.

Approach

Prunes visual tokens while correcting positional bias in the selection signal, rather than relying on global [CLS]-attention selection or in-LLM pruning. Only the abstract is available, so the precise mechanism is not described.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use ARP instead of global [CLS] selection at 352 tokens (ablation)PosPrune (LLaVA-1.5-7B) · MMEscore: 1687 -> 1751Improved
use ARP instead of global [CLS] selection at 352 tokens (ablation)PosPrune (LLaVA-1.5-7B) · ScienceQAaccuracy: 67.4 -> 67.7Improved
add MMR and prune to 72 tokens (ablation)PosPrune (LLaVA-1.5-7B) · MMEscore: 1751 -> 1746No clear effect
add Positional Bias Correction (ablation)PosPrune (LLaVA-1.5-7B) · MMEscore: 1746 -> 1792Improved
add Positional Bias Correction (ablation)PosPrune (LLaVA-1.5-7B) · ScienceQAaccuracy: 67.8 -> 68.2Improved
use polynomial degree 3 instead of degree 1 for bias fit (ablation)PosPrune (LLaVA-1.5-7B) · MMEscore: 1765 -> 1792Improved
use polynomial degree 3 instead of degree 5 for bias fit (ablation)PosPrune (LLaVA-1.5-7B) · MMEscore: 1663 -> 1792Improved
use degree 3 instead of degree 2 polynomial (ablation)PosPrune (LLaVA-1.5-7B) · ScienceQAaccuracy: 68.1 -> 68.2No clear effect
use MMR with lambda 0.9 instead of relevance-only (lambda 1) (ablation)PosPrune (LLaVA-1.5-7B) · MME and ScienceQAscoreImproved
fit bias with 800 samples instead of fewer (ablation)PosPrune (LLaVA-1.5-7B) · MME and ScienceQAscoreImproved
PosPrune instead of VisionZipLLaVA-1.5-7B · 8 image benchmarks (average)performance retained: 96.7% -> 98.5%Improved
PosPrune instead of VisionZipQwen2.5-VL-7B · 8 image benchmarks (average)performance retained: 95.3% -> 97.8%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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.

Limitations

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