AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models

Vittorio Pipoli, Alessia Saporita, Federico Bolelli, Marcella Cornia, Lorenzo Baraldi, Costantino Grana, Rita Cucchiara, Elisa Ficarra

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Unified any-modality language models · 8 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 MissRAG+PEChatBridge · MUSIC-AVQA (missing video)accuracy: 27.25 -> 43.18Improved
add MissRAG+PEOneLLM · VALOR-32K (missing video)CIDEr: 3.34 -> 16.57Improved
add MissRAG+PEVideoLLaMA 2 · MUSIC-AVQA (missing video)accuracy: 59.57 -> 60.11Improved
add MissRAG+PEOneLLM · MOSI (missing audio)accuracy: 48.54 -> 78.57Improved
add MissRAG+PEVideoLLaMA 2 · MOSI (missing audio)accuracy: 46.06 -> 33.38Hurt
add MissRAG+PEVideoLLaMA 2 · MOSEI (missing audio)accuracy: 41.36 -> 38.63Hurt
add prompt engineering alone (ablation)OneLLM · MOSEI (missing video)accuracy: 57.70 -> 64.58Improved
add MissRAG retrieval on top of PE (ablation)OneLLM · MUSIC-AVQA (missing video)accuracy: 41.81 -> 46.66Improved
add MissRAG retrieval on top of PE (ablation)OneLLM · MOSI (missing video)accuracy: 79.74 -> 74.49Hurt
add PE on top of MissRAG retrieval (ablation)OneLLM · MUSIC-AVQA (missing video)accuracy: 45.55 -> 46.66Improved
increase retrieved prototypes k from 1 to 5 (with PE) (ablation)OneLLM · MUSIC-AVQA (missing video)accuracy: 46.66 -> 47.29No clear effect
use merged prototype pool across datasets (ablation)OneLLM · MUSIC-AVQA (missing video)accuracy: 46.66 -> 46.57No 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