AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models

Walid Bousselham, Angie Boggust, Hendrik Strobelt, Hilde Kuehne

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Attention-based visual token pruning · 2 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 dynamic head filtering (max-based) (ablation)DEX-AR · PascalVOC (LLaVA)SNR: 1.64 -> 3.64Improved
add dynamic head filtering (max-based) (ablation)DEX-AR · PascalVOC (BakLLaVA)SNR: 5.27 -> 6.02Improved
score heads by max instead of average gradient (ablation)DEX-AR · PascalVOC (LLaVA)SNR: 1.09 -> 3.64Improved
score heads by top-0.05 gradients instead of max (ablation)DEX-AR · PascalVOC (LLaVA)SNR: 3.64 -> 3.35Hurt
add head filtering alone (ablation)DEX-AR · PascalVOC-QA (LLaVA-1.5-7B)SNR: 9.16 -> 16.84Improved
add filler-token filtering alone (ablation)DEX-AR · PascalVOC-QA (LLaVA-1.5-7B)SNR: 9.16 -> 89.29Improved
add head filtering on top of filler filtering (ablation)DEX-AR · PascalVOC-QA (LLaVA-1.5-7B)SNR: 89.29 -> 96.12Improved
add head filtering on top of filler filtering (ablation)DEX-AR · PascalVOC-QA (LLaVA-1.5-7B)MSE: 0.11 -> 0.12Hurt
add ReLU on attention gradients (ablation)DEX-AR · PascalVOC (LLaVA)IoU: 31.56 -> 36.34Improved
use intermediate layers instead of last layer only (ablation)DEX-AR · PascalVOC (LLaVA)IoU: 33.05 -> 36.34Improved
use intermediate layers instead of last layer only (ablation)DEX-AR · PascalVOC (Florence-2)IoU: 26.91 -> 32.48Improved
add ReLU on attention gradients (ablation)DEX-AR · PascalVOC (PaliGemma)IoU: 22.90 -> 23.55No clear effect

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.

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