AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

DIVA: Instruction-Aware Vision Token Pruning via Dual-Probe Attention Discrepancy

Hyunwoo Kim, Kisu Lee, Yuna Shin, Ha Young Kim

ECCV 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. 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 DIVA-Pruner (CS score selection) (ablation)DIVA · LLaVA-1.5-7B, 64 tokens kept (ablation)relative performance vs unpruned (%): 87.9% -> 97.8%Improved
add VF-Calibrator (ablation)DIVA · LLaVA-1.5-7B, 64 tokens kept (ablation)relative performance vs unpruned (%): 87.9% -> 95.6%Improved
add VF-Calibrator on top of DIVA-Pruner (ablation)DIVA · LLaVA-1.5-7B, 64 tokens kept (ablation)relative performance vs unpruned (%): 97.8% -> 98.8%Improved
use suffix plus similarity-selected instruction tokens as contextual probes instead of last text token (ablation)DIVA · LLaVA-1.5-7B, 64 tokens kept (ablation)relative performance vs unpruned (%): 95.1% -> 98.8%Improved
use all instruction plus suffix tokens instead of similarity-selected subset (ablation)DIVA · LLaVA-1.5-7B, 64 tokens kept (ablation)relative performance vs unpruned (%): 98.6% -> 98.8%No clear effect
forward KLD instead of reverse KLD (ablation)DIVA · LLaVA-1.5-7B, 64 tokens kept (ablation)relative performance vs unpruned (%): 95.9% -> 98.8%Improved
forward KLD instead of JSD or CFG variants (ablation)DIVA · LLaVA-1.5-7B, 64 tokens kept (ablation)relative performance vs unpruned (%): 98.1% -> 98.8%No clear effect
raise gamma from 0.1 to 0.5 (ablation)DIVA · LLaVA-1.5-7B, 64 tokens kept (ablation)relative performance vs unpruned (%): 98.8% -> 92.7%Hurt
raise gamma from 0.1 to 0.3 (ablation)DIVA · LLaVA-1.5-7B, 64 tokens kept (ablation)relative performance vs unpruned (%): 98.8% -> 98.4%No clear effect
DIVA vs CDPruner at 64 tokensDIVA · LLaVA-1.5-7B, 64 tokens keptrelative performance vs unpruned (%): 98.6% -> 99.8%Improved
DIVA vs PDrop at 10% tokens on Qwen3-VL-8BDIVA · Qwen3-VL-8B, 10% tokens keptrelative performance vs unpruned (%): 68.1% -> 82.6%Improved
DIVA vs CDPruner on video at 16 tokens per frameDIVA · LLaVA-Video-7B, 64x16relative performance vs unpruned (%): 90.2% -> 94.5%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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