MemGraphRAG introduces a novel memory-based multi-agent system to construct globally consistent and structurally sound knowledge graphs, significantly improving retrieval-augmented generation for comp…

The paper systematically compares multimodal transformer and LLM approaches for document type classification, finding that specialized multimodal Transformers outperform LLM-based models, especially w…

The paper introduces MechVQA, a comprehensive dataset and benchmark for mechanical drawing understanding, and proposes the MechVL model, which significantly improves Multimodal LLMs' performance on th…

TRIAGE is a framework for evaluating and diagnosing failures in document-grounded graph-RAG systems by attaching stage-specific metrics.

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

This paper introduces SVD-RAG, a cost-efficient and content-adaptive summarization method for hierarchical Retrieval-Augmented Generation systems using Singular Value Decomposition on dense sentence e…

The paper introduces ChartWalker, a framework for generating challenging cross-modal analytical tasks using charts, with a hierarchical knowledge graph construction method and structure-aware sampling…

The paper systematically evaluates advanced retrieval-augmented generation (RAG) architectures for Cyber Threat Intelligence (CTI), demonstrating that a hybrid graph-text approach significantly improv…

The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving sta…

The paper introduces PlanRAG, a framework for Retrieval-Augmented Generation (RAG) that models exploratory reasoning problems as logical query trees, addressing representation and optimization gaps be…

HiKEY proposes a hierarchical, tree-based multimodal retrieval framework that significantly improves open-domain document question answering by addressing document routing and evidence fragmentation.

This paper introduces KGERMAR, a framework that constructs dynamic, context-specific knowledge graphs during inference for long-context language modeling, achieving lower perplexity and better memory…

This paper introduces MMed-Bench-IR, a benchmark for multilingual medical retrieval in clinical settings, evaluating cross-lingual alignment, concept discrimination, and evidence retrieval.

This paper introduces ClinFusion, a vision-centric multimodal large language model designed for holistic medical understanding, featuring a Cascade Spatial-Aware Locality Fusion operator and a vision-…

The paper proposes a zero-shot multi-label topic classification framework and finds that while knowledge graph augmentation improves performance for smaller language models, it offers diminishing retu…

The paper introduces TechGraphRAG, an advanced, agentic RAG framework that enhances technical literature reasoning by integrating multi-step query refinement, external database searching, and knowledg…

The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that curre…