UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities

arXiv:2504.20734 · cs.CL, cs.AI, cs.CV, cs.IR, cs.LG · Submitted 2025-04-29 · Read on arXiv

cs.CL, cs.AI, cs.CV, cs.IR, cs.LG

Submitted: 2025-04-29

Updated: 2026-06-12

Code: https://github.com/Breakthrough/PySceneDetect

Project page: https://universalrag.github.io

Terminology

• RAG — 72× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation — 47× in this paper
• Benchmark — 36× in this paper · explained in 2 episodes
• Accuracy — 20× in this paper · explained in 1 episode
• Modality Gap — 15× in this paper · explained in 4 episodes
• Embeddings — 7× in this paper · explained in 2 episodes
• Grounding — 6× in this paper · explained in 3 episodes
• Multi-hop Reasoning — 6× in this paper · explained in 3 episodes
• Empirical Methods in Natural Language Processing — 5× in this paper
• Hallucination — 5× in this paper · explained in 4 episodes
• Natural Questions — 5× in this paper
• Benchmarking — 4× in this paper · explained in 4 episodes
• Core — 4× in this paper · explained in 2 episodes
• Canadian Football League — 3× in this paper
• Generalization — 3× in this paper · explained in 13 episodes
• Retrieval-Augmented Generation (RAG) — 3× in this paper · explained in 16 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Adaptive Planning — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Exact Match — 1× in this paper
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hallucination Mitigation — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Meta-learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Qwen3-VL Technical Report
• Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Gemini: A Family of Highly Capable Multimodal Models
• RAG-Anything: All-in-One RAG Framework
• E5-V: Universal Embeddings with Multimodal Large Language Models
• LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
• Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
• SmolVLM: Redefining small and efficient multimodal models
• GPT-4o System Card
• OpenAI GPT-5 System Card
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries
• Corrective Retrieval Augmented Generation
• T5Gemma 2: Seeing, Reading, and Understanding Longer
• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering