大模型
arxiv.org ·
Q-CueGraph：用于多模态推理的查询条件视觉证据图
该论文提出 Q-CueGraph，一种面向冻结多模态大模型的查询条件化证据获取方法。对文本密集图像，它构建 OCR 行与版面关系的可复用图，每个问题激活锚点、扩展为上下文区域并选出单一观察窗口；自然图像则通过查询条件化目标检测复用同一区域选择与组合接口。轻量候选打分器从冻结读者反馈和训练答案中学习哪些观察支持正确答案，无需证据框监督。在六个基准上，使用 Qwen2.5-VL-7B 时 V*Bench 准确率由 0.696 升至 0.832，仅用源图 19.1% 面积；InfographicVQA 上以约一半图像面积保留全图 ANLS 的 92%。分析表明有用证据同时取决于与问题的相关性和读者可用的上下文。
AI推荐理由 arXiv 论文（v2，2026-09-24 修订），摘要给出明确方法与量化结果：Q-CueGraph 为冻结 MLLM 提供查询条件化的视觉证据获取，在文本密集图像上构建 OCR 行与版面关系的可复用图，问题激活锚点并扩展为上下文区域，选出单一观察窗口；自然图像用查询条件化目标检测走同一区域选择接口；轻量候选打分器从冻结读者反馈与训练答案学习可答性，无需证据框监督。在六个基准上评估，Qwen2.5-VL-7B 下 V*Bench 准确率从 0.696 提升到 0.832，仅用源图 19.1% 面积；InfographicVQA 上以约一半图像面积保留全图 ANLS 的 92%。局限：仅摘要级证据，未提供代码/复现细节，效果依赖特定模型与基准。
78
正文
Computer Science > Computer Vision and Pattern Recognition
arXiv:2608.04452 (cs)
[Submitted on 5 Aug 2026 (v1), last revised 24 Sep 2026 (this version, v2)]
Title:Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning
Authors:Pengcheng Pan, Xinfang Zhang
View a PDF of the paper titled Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning, by Pengcheng Pan and Xinfang Zhang
View PDF
HTML (experimental)
Abstract:Multimodal large language models (MLLMs) can miss fine details in a full image that they recognize in a closer view. Recovering this evidence requires deciding where to look and how much surrounding context to retain. We present Q-CueGraph, a query-conditioned evidence acquisition method for frozen MLLMs. For text-rich images, it builds a reusable graph of OCR lines and layout relations. Each question activates anchors, expands them into contextual regions, and selects candidates for a single observation window. Query-conditioned object detections support natural-image search through the same region-selection and composition interface. A lightweight candidate scorer further learns which observations support correct answers from frozen-reader feedback and training answers, without evidence-box supervision. Across six benchmarks, we examine the roles of query conditioning, evidence composition, and learned answerability. With Qwen2.5-VL-7B, Q-CueGraph raises V*Bench accuracy from 0.696 to 0.832 using 19.1% of source-image area, and retains 92% of full-image ANLS on InfographicVQA using about half the image area. The analyses show that useful evidence depends on both its relevance to the question and the context available to the reader. Q-CueGraph makes these choices explicit before answer generation.
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as:
arXiv:2608.04452 [cs.CV]
(or
arXiv:2608.04452v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.04452
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Pengcheng Pan [view email]
[v1]
Wed, 5 Aug 2026 05:03:35 UTC (6,191 KB)
[v2]
Thu, 24 Sep 2026 17:41:40 UTC (6,816 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Q-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning, by Pengcheng Pan and Xinfang Zhang
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new
|
recent
| 2026-08
Change to browse by:
cs
cs.AI
cs.CL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)