A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This survey introduces Large Multimodal Reasoning Models (LMRMs) and proposes the concept of native LMRMs (N-LMRMs) that integrate perception, reasoning, and planning.
Unknown
CEMRAG integrates interpretable visual concept extraction with multimodal RAG to improve both interpretability and factual accuracy in radiology report generation.
Unknown
HierFinRAG uses hierarchical multimodal RAG with Symbolic–Neural Fusion to close 60–80% of the human–AI performance gap on financial document understanding.
Unknown
This paper proposes QIMG-7 and source-aware resolution to improve multimodal RAG reliability by resolving conflicts before fusion.
Unknown
This paper proposes a reliable multimodal RAG method for medical vision-language models to improve factual accuracy.
Unknown
This paper explores optimal configurations for multimodal RAG systems, showing they can outperform single-modality RAG in industrial applications.
Unknown
Introduces a unified benchmark for multimodal RAG evaluation using real-world PDF documents and a data synthesizing pipeline.
Junxiao Xue, Quan Deng, Fei Yu, et al.
Enhanced multimodal RAG-LLM framework for accurate visual question answering by integrating retrieval-augmented generation with multimodal data.
Unknown
Formalizes and addresses parametric-retrieved and visual-textual knowledge inconsistencies in multimodal RAG via cross-source reconciliation.
Unknown
M4-RAG is an evaluation framework for multilingual, multicultural, and multimodal RAG that focuses on end-to-end task performance and systematic failure analysis.
Unknown
MMed-RAG is a versatile multimodal RAG system designed for medical vision-language models to generate more factual responses.
Unknown
This survey comprehensively reviews benchmark evaluations, applications, and challenges of large vision-language models, synthesizing progress across multimodal AI.