Multimodal Graph RAG for Long-range Visually Rich Document Understanding
cs.IR, cs.CV
Submitted: 2026-06-27
Updated: 2026-11-05
Code: https://github.com/AIApplication-and-Integration-Lab/KG4VD
Terminology
Sources
- Qwen2.5-VL Technical Report
- PaliGemma: A versatile 3B VLM for transfer
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- RAG-Anything: All-in-One RAG Framework
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
- Gemma 3 Technical Report
- MinerU: An Open-Source Solution for Precise Document Content Extraction
- Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Related papers
- UniRank: Benchmarking Ranking Models for Unified Sequential Modeling and Feature Interaction
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA