AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Benchmarking Multimodal Large Language Models Against Image Corruptions

Xinkuan Qiu, Meina Kan, Yongbin Zhou, Shiguang Shan

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Benchmarks and analysis of MLLMs · 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
increase corruption severity to most severe levelGPT-4o · MLLM-ICaccuracy: 14.3% dropHurt
increase corruption severity to most severe levelDeepSeek-VL · MLLM-ICaccuracy: 5.8% -> 9.8% dropHurt
blur corruption versus geometric transformsGPT-4o · MLLM-ICaccuracy: 68.6 -> 53.0Hurt
blur corruption versus geometric transformsGemini 2.0 · MLLM-ICaccuracy: 77.2 -> 64.3Hurt
compression versus geometric corruptionQwen2.5-VL · MLLM-ICaccuracy: 75.0 -> 64.1Hurt
spatial perception versus global context sensingQwen2.5-VL · MLLM-ICaccuracy: 73.2 -> 64.3Hurt
knowledge reasoning versus logical reasoningLLaVA-1.5 · MLLM-ICaccuracy: 66.1 -> 47.0Hurt
larger or proprietary model Gemini 2.0 versus LLaVA-1.5Gemini 2.0 · MLLM-ICaccuracy: 63.6 -> 76.2Improved

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