AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes

Paul Gavrikov, Wei Lin, M. Jehanzeb Mirza, Soumya Jahagirdar, Muhammad Huzaifa, Sivan Doveh, James Glass, Serena Yeung-Levy, Hilde Kuehne

CVPR 2026 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 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 zero-shot chain-of-thought prompting (ablation)InternVL3 38B · VisualOverload totalaccuracy: 67.6 -> 65.5Hurt
add zero-shot chain-of-thought prompting (ablation)InternVL3 38B · VisualOverload hard splitaccuracy: 7.2 -> 14.4Improved
add zero-shot chain-of-thought prompting (ablation)InternVL3 38B · VisualOverload OCRaccuracy: 45.8 -> 50.0Improved
add zero-shot chain-of-thought prompting (ablation)InternVL3 38B · VisualOverload reasoningaccuracy: 69.8 -> 62.4Hurt
scale InternVL3 from 38B to 78BInternVL3 · VisualOverload totalaccuracy: 67.6 -> 66.8Hurt
scale PaliGemma 2 from 10B to 28BPaliGemma 2 · VisualOverload totalaccuracy: 50.3 -> 41.5Hurt
scale Qwen2.5-VL from 3B to 7BQwen2.5-VL · VisualOverload totalaccuracy: 54.1 -> 61.5Improved
use specialized high-resolution model instead of regular modelVILA HD 4K vs Qwen2.5-VL 7B · VisualOverload totalaccuracy: 61.5 -> 48.5Hurt
allow 10% tolerance in counting answersall evaluated VLMs · VisualOverload countingaccuracy: +1.6%No clear effect
move from scene classification to reasoning questions (logical consistency)frontier VLMs · VisualOverloadlogical consistency (%): 83.3 -> 60.6Hurt
increase image resolution up to Full HD (ablation)InternVL3 · VisualOverloadaccuracyImproved

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