mlsanityData to 14 Oct 2026

Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation

arXiv 2609.19634 ↗First posted 17 Sep 2026cs.CV cs.CLcited by 0

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

This paper proposes a Retrieval-Augmented Generation (RAG) framework for scientific image quality assessment, designed to simultaneously address both the understanding track (SIQA-U) and the scoring track (SIQA-S) of the SIQA challenge. We construct a multimodal index that integrates textual semantics with fine-grained visual features, and develop a multi-route retrieval and fusion mechanism to provide large language models with highly relevant reference cases, thereby enhancing their capability to evaluate complex scientific images. Experimental results demonstrate that the proposed framework effectively aligns with the judgment criteria of human experts. Ultimately, our method achieves 1st place in the SIQA-U track of the SIQA challenge at the ICME 2026 Grand Challenges.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 10 of its 13 references that are in the map. First posted on arXiv 17 Sep 2026.

Builds on

10 of 13 references.

References · 10

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  4. 2023A Survey on Multimodal Large Language Modelscited by 909
  5. 2024PaliGemma: A versatile 3B VLM for transfercited by 696
  6. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  7. 2024ColPali: Efficient Document Retrieval with Vision Language Modelscited by 195
  8. 2024A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessmentcited by 43
  9. 2026SIQA: Toward Reliable Scientific Image Quality Assessmentcited by 4
  10. 2025Max360IQ: Blind Omnidirectional Image Quality Assessment with Multi-axis Attentioncited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models
  2. 2025Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook
  3. 2026SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context
  4. 2024SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
  5. 2026SpecVQA: A Benchmark for Spectral Understanding and Visual Question Answering in Scientific Images
  6. 2025Re-ranking the Context for Multimodal Retrieval Augmented Generation
  7. 2025Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries
  8. 2026KIRA: Knowledge-Intensive Image Retrieval and Reasoning Architecture for Specialized Visual Domains