浙大提出評估框架

Computer Science > Computer Vision and Pattern Recognition arXiv:2607.

21072 (cs) [Submitted on 23 Jul 2026] Title:Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text Authors:Xu Wang, Kaixiang Yao, Miao Pan, Xiaohe Zhou, Xuanyu Liu, Wenqi Zhang, Xuhong Zhang View a PDF of the paper titled Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text, by Xu Wang and 6 other authors View PDF HTML (experimental) Abstract:Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world.

Many spatial tasks are grounded in continuous visual scenes, where locations, regions, and paths are more naturally expressed by pointing, marking, or drawing than by reporting precise coordinates or discrete textual symbols.

Yet existing spatial reasoning benchmarks usually require coordinates, options, or text, creating an answer-interface mismatch for image-generation models.

This makes it difficult to evaluate image-generation models under the same task semantics as text-output VLMs, despite their ability to externalize spatial judgments directly in pixel space.

We propose ProVisE (Protocolized Visual Evaluation), a benchmark-agnostic framework that elicits protocol-constrained visual answers from image-generation models and parses them into structured predictions compatible with original metrics.

ProVisE also includes an Agentic builder that constructs and validates task-specific protocols for new benchmarks.We further introduce SpatialGen-Bench, a curated diagnostic benchmark of 470 samples across 14 spatial subtasks, four capability levels, and diverse answer forms.

We evaluate representative text-output VLMs and image-generation models in a unified setting and validate Agentic protocol construction on six external spatial benchmarks.

Results show that image-generation models are competitive when spatial answers can be externalized directly in pixel space, while text-output VLMs retain a clear advantage in compositional spatial reasoning.

These findings reveal complementary strengths of pixel-space expression and text-based reasoning and establish a metric-compatible testbed for studying spatial cognition in image-generation models.Comments: 36 pages, 14 figures.

Project page: this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2607.21072 [cs.CV] (or arXiv:2607.21072v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2607.

21072 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Xu Wang [view email] [v1] Thu, 23 Jul 2026 09:04:48 UTC (26,111 KB) Full-text links: Access Paper: View a PDF of the paper titled Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text, by Xu Wang and 6 other authorsView PDFHTML (experimental)TeX Source view license Current browse context: cs.

CV < prev | next > new | recent | 2026-07 Change to browse by: cs References & Citations NASA ADSGoogle 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?)