AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models

Zhen Zeng, Leijiang Gu, Xun Yang, Zhangling Duan, Zenglin Shi, Meng Wang

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 11 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
replace text-only scope classifier with multimodal scope classifier (ablation)SERAC (BLIP-2 OPT) · FGVEditspecificity (%): 31.92 -> 61.60Improved
replace text-only scope classifier with multimodal scope classifier (ablation)SERAC (MiniGPT-4) · FGVEditspecificity (%): 37.85 -> 57.20Improved
add multimodal scope classifier to MEND (MSCKE-MEND) (ablation)MEND (BLIP-2 OPT) · FGVEditspecificity (%): 65.85 -> 68.38Improved
add multimodal scope classifier to MEND (MSCKE-MEND) (ablation)MEND (MiniGPT-4) · FGVEditspecificity (%): 67.39 -> 71.98Improved
replace text-only scope classifier with multimodal scope classifier (ablation)SERAC (BLIP-2 OPT) · FGVEditreliability (%): 93.08 -> 99.13Improved
replace text-only scope classifier with multimodal scope classifier (ablation)SERAC (MiniGPT-4) · FGVEditreliability (%): 99.50 -> 99.50No clear effect
add multimodal scope classifier to MEND (ablation)MEND (MiniGPT-4) · FGVEditreliability (%): 94.85 -> 97.05Improved
replace text-only scope classifier with multimodal scope classifier (ablation)SERAC (BLIP-2 OPT) · FGVEditgenerality (%): 96.83 -> 98.56Improved
replace text-only scope classifier with multimodal scope classifier (ablation)SERAC · MMEdit (VQA)M-Locality (%): 2.91 -> 98.08Improved
replace text-only scope classifier with multimodal scope classifier (ablation)SERAC · MMEdit (VQA)T-Generality (%): 99.90 -> 95.60Hurt
add multimodal scope classifier to MEND (ablation)MEND · MMEdit (VQA)T-Generality (%): 97.51 -> 92.10Hurt
transfer classifier trained on BLIP-2 OPT to MiniGPT-4 instead of retraining (ablation)MSCKE · FGVEditspecificity (%): 57.09 -> 57.20No clear effect

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