AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Generalize LMMs to Versatile Visual Modalities via Fabricated Modality Synthesis

Shihao Yuan, Yuanze Li, Ruyi Zhang, Ming LIU, Wangmeng Zuo

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 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
apply VVM-Tuning (modality synthesis + modality contexts)LLaVA-1.5 7B · VVM-Bench perception averageaccuracy: 60.4% -> 74.1%Improved
apply VVM-TuningQwen-3-VL 4B · VVM-Bench perception averageaccuracy: 77.6% -> 82.8%Improved
apply VVM-TuningLLaVA-1.5 7B · VVM-Bench understanding averageaccuracy: 79.4% -> 84.9%Improved
apply VVM-TuningQwen-3-VL 4B · VVM-Bench understanding averageaccuracy: 87.9% -> 89.9%Improved
apply VVM-TuningLLaVA-1.5 7B · VVM-Bench perception, Optical Flowaccuracy: 53.2% -> 75.4%Improved
add modality context in the prompt (ablation)Base LMMs and VVM-Tuned models · VVM-Bench understanding, Thermal/Depth/X-Rayaccuracy: 15.37% (Thermal), 32.75% (Depth), 3.05% (X-Ray) average gainImproved
add modality-unaware perception tasks (ablation)VVM-Tuning · VVM-Bench perception averageaccuracy: 78.1% -> 81.7%Improved
add modality-unaware perception tasks (ablation)VVM-Tuning · VVM-Bench understanding averageaccuracy: 86.2% -> 88.3%Improved
add modality-aware understanding tasks without perception tasks (ablation)VVM-Tuning · VVM-Bench perception averageaccuracy: 78.1% -> 78.0%No clear effect
add modality-aware understanding tasks on top of perception tasks (ablation)VVM-Tuning · VVM-Bench perception averageaccuracy: 81.7% -> 84.1%Improved
add modality-aware understanding tasks on top of perception tasks (ablation)VVM-Tuning · VVM-Bench understanding averageaccuracy: 88.3% -> 90.6%Improved
increase training data from 25% to 100% (ablation)VVM-Tuning · VVM-Bench perception averageaccuracy: 81.9% -> 84.1%Improved

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