如何想象、想象什么？统一多模态模型跨视角空间推理中的视觉思维

Computer Science > Computer Vision and Pattern Recognition arXiv:2605.27310 (cs) [Submitted on 26 May 2026 (v1), last revised 14 Sep 2026 (this version, v2)] Title:How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning Authors:Qian Yang, Ankur Sikarwar, Huy Le, Le Zhang, Zhuan Shi, Perouz Taslakian, Aishwarya Agrawal View a PDF of the paper titled How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning, by Qian Yang and 6 other authors View PDF HTML (experimental) Abstract:Cross-view spatial reasoning remains a weak spot for vision-language models (VLMs): they reason in language and discard the fine-grained geometry the task requires. Thinking with images aims to fix this by generating an intermediate thinking-image, but recent work shows the visual evidence in these traces is largely ignored. We therefore ask how to make visual thinking matter, and what kind of visual thinking works best. We ask these questions for unified multimodal models (UMMs) that natively support interleaved image-text generation. For the how, we propose View Dropout (VDrop), a training-time intervention that hides parts of one input view from the answer span while leaving it visible to the thinking-image tokens. This incentivizes the model to make use of the thinking-image when answering, rather than answering based on the input views only. With the thinking-image now being used in answer prediction, we ask which kind of visual thinking works best. We frame this as a Learnability-Informativeness (L-I) tradeoff and compare three thinking-image variants: top-down, panoramic, and point-matching renderings. Trained on synthetic scenes and evaluated on five real-world out-of-domain benchmarks, panoramic visual thinking with VDrop is the only configuration that is simultaneously informative and learnable, and achieves the best out-of-domain generalization. Comments: Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2605.27310 [cs.CV] (or arXiv:2605.27310v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2605.27310 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Qian Yang [view email] [v1] Tue, 26 May 2026 17:20:05 UTC (20,031 KB) [v2] Mon, 14 Sep 2026 08:22:13 UTC (20,250 KB) Full-text links: Access Paper: View a PDF of the paper titled How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning, by Qian Yang and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV new | recent | 2026-05 Change to browse by: cs 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?)