{"slug": "from-hallucination-to-grounding-diagnosing-visual-spatial-intelligence-via-crisp", "title": "From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP", "summary": "Researchers introduced CRISP, a new evaluation paradigm that diagnoses visual spatial intelligence in vision-language models by measuring consistency between implicit perception and explicit reasoning. The study found that proprietary models have strong reasoning engines but fail to leverage structural representations, while open-source models lack multi-hop compositional reasoning.", "body_md": "arXiv:2606.26535v1 Announce Type: new\nAbstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evaluation paradigm that assesses visual spatial intelligence through consistency, the alignment between implicit perception and explicit reasoning. Unlike traditional black-box QA, CRISP utilizes metric 3D Scene Graphs and an oracle intervention protocol to decouple latent reasoning capabilities from perceptual bottlenecks. This granular diagnosis uncovers a systematic perception-reasoning disconnect. Crucially, we reveal that while proprietary models possess robust latent reasoning engines, they suffer from inaccurate metric estimation and a critical failure to leverage their implicit structural representations. Conversely, open-source models remain fundamentally bottlenecked by their lack of multi-hop compositional reasoning. By shifting the focus from merely ``guessing correctly'' via language priors to genuinely `` perceiving, verifying, and reasoning,'' CRISP offers a rigorous roadmap for multimodal alignment beyond end-to-end post-training. The code and dataset are available at https://github.com/iiyamayuki/CRISP-Bench.", "url": "https://wpnews.pro/news/from-hallucination-to-grounding-diagnosing-visual-spatial-intelligence-via-crisp", "canonical_source": "https://arxiv.org/abs/2606.26535", "published_at": "2026-06-26 04:00:00+00:00", "updated_at": "2026-06-26 04:09:48.346534+00:00", "lang": "en", "topics": ["computer-vision", "natural-language-processing", "ai-research"], "entities": ["CRISP", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/from-hallucination-to-grounding-diagnosing-visual-spatial-intelligence-via-crisp", "markdown": "https://wpnews.pro/news/from-hallucination-to-grounding-diagnosing-visual-spatial-intelligence-via-crisp.md", "text": "https://wpnews.pro/news/from-hallucination-to-grounding-diagnosing-visual-spatial-intelligence-via-crisp.txt", "jsonld": "https://wpnews.pro/news/from-hallucination-to-grounding-diagnosing-visual-spatial-intelligence-via-crisp.jsonld"}}