AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

SPIDER: Multi-Layer Semantic Token Pruning and Adaptive Sub-Layer Skipping in Multimodal Large Language Models

Tianxiang Chen, Zhentao Tan, Zi Ye, Yue Wu, Xiaobing Tu, Jinkui Ren, Xiantao Zhang, Tao Gong, Qi Chu, Nenghai Yu, Xipeng Qiu, Jieping Ye

TPAMI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Training-free token reduction for MLLMs · 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 semantic clustering (ablation)MSV-Prune · LLaVA-NeXT-7B 1920 tokensrelative accuracy: 99.33% -> 100.64%Improved
add middle-layer tokens (ablation)MSV-Prune · LLaVA-NeXT-7B 1920 tokensrelative accuracy: 99.13% -> 100.64%Improved
add inter-layer similarity term (ablation)MSV-Prune · LLaVA-NeXT-7B 1920 tokensrelative accuracy: 99.60% -> 100.64%Improved
add similarity with anchor tokens (ablation)MSV-Prune · LLaVA-NeXT-7B 1920 tokensrelative accuracy: 100.20% -> 100.64%Improved
use 4 clusters instead of 8 (ablation)MSV-Prune · LLaVA-NeXT-7B 1920 tokensrelative accuracy: 99.68% -> 100.64%Improved
use anchor ratio 0.7 instead of 0 (ablation)MSV-Prune · LLaVA-1.5-7Brelative accuracy: 95.74% -> 99.56%Improved
use anchor ratio 0.7 instead of 1.0 (ablation)MSV-Prune · LLaVA-1.5-7Brelative accuracy: 98.74% -> 99.56%Improved
add sub-layer contribution (SLC) to fusion score (ablation)ASL-Skip · LLaVA-1.5-7Brelative accuracy: 98.30% -> 99.81%Improved
add online skippability score S_sa (ablation)ASL-Skip · LLaVA-1.5-7Brelative accuracy: 99.17% -> 99.81%Improved
add accumulation of skip score (ablation)ASL-Skip · LLaVA-1.5-7Brelative accuracy: 99.22% -> 99.81%Improved
skip all FFN sub-layers for visual tokens (ablation)ASL-Skip · LLaVA-1.5-7Brelative accuracy: 99.81% -> 71.34%Hurt
fine-tune SPIDER (training-aware) instead of training-freeSPIDER · LLaVA-1.5-7B ~30% TFLOPsrelative accuracy: 99.0% -> 99.5%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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.

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