{"article":{"annotation":{"article_id":"mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026","available_at":"2026-10-20T14:20:52.389732Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"e5710278f8cec0a2906dc7203859df54ebf4270e4b158bf1095789cd6bb96343","input_sha256":"8f58a4ddf0ae24478d8f2b083e5b695e3c8340ab159d0fc8638e63190d3f5dda","limitations":["Rule-derived subjects are candidates, not verified editorial labels or calibrated model probabilities.","Coverage is distinct from event location. Unknown country/city/coordinates remain absent; no automatic geocoding.","Article geometries keep their stated precision and methodology; reproducing them is not independent coordinate verification."],"method":"controlled-rules-v1","places":[{"admin1":null,"city":null,"coordinate_note":null,"coordinate_reference_system":"OGC:CRS84","coordinate_source":null,"country":"AE","evidence":[{"field":"country","language":"en","note":"Explicit preserved editorial country/region; no city or national centroid inferred","source_urls":["https://mbzuai.ac.ae/news-events/news/building-llm-can-reason-about-the-physical-3d-world-fine-grained-level"]}],"geometry":null,"id":"iso3166-1:AE","kind":"country-or-area","labels":{"ar":"الإمارات العربية المتحدة","en":"United Arab Emirates","es":"Emiratos Árabes Unidos","fr":"Émirats arabes unis"},"match_status":"candidate","precision":"regional","role":"coverage","uncertainty_m":null}],"rules_sha256":"fb5ad3c27c91cb840f7a0a05f7f64a5cb26ad0374409ff9457f277c7092e22b4","schema_version":1,"subjects":[{"concept_id":"medtop:13000000","confidence":null,"confidence_method":null,"evidence":[{"field":"category+topics","language":"en","note":"Preserved editorial category/topic; broad candidate only","source_urls":["https://mbzuai.ac.ae/news-events/news/building-llm-can-reason-about-the-physical-3d-world-fine-grained-level"]}],"method":"controlled-rules-v1","rule_id":"technology-broad","status":"candidate"}],"taxonomy_revision":"1f2db31d811fca07e99b16d402c10e2cc2965c9df1c7b41d9be348b40a24e7fb","taxonomy_version":"IPTC Media Topics 2026-Q2"},"api_url":"https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026?lang=es","category":"technology","content":{"key_points":[],"paragraphs":["Ground3D-LMM, desarrollado por investigadores de MBZUAI, combina instrucciones de texto con nubes de puntos 3D para localizar y medir objetos y partes concretas de una escena. Según una nota de la universidad del 20 de octubre, el modelo se entrenó y evaluó con un conjunto de datos creado a partir de ScanNet y ScanNet++, con anotaciones de objetos y sus partes.","El conjunto contiene unos 2,5 millones de pares de preguntas y respuestas, alrededor de 2.500 entornos interiores y ocho tareas. MBZUAI informó que Ground3D-LMM superó a otros sistemas por cerca del 20% en ScanRefer sin usar imágenes 2D; es un resultado comparativo en una prueba de investigación específica. Los resultados se presentaron en ECCV 2026. El estudio no demuestra capacidad robótica en el mundo real ni mediciones físicas fiables."],"sections":[]},"corrections":[],"country":"AE","data":{"blocks":[{"columns":[{"key":"label","label":{"ar":"المؤشر","de":"Indikator","en":"Indicator","es":"Indicador","fr":"Indicateur","pt":"Indicador","tr":"Gösterge"},"language":"en","type":"text"},{"key":"value","label":{"ar":"القيمة","de":"Wert","en":"Value","es":"Valor","fr":"Valeur","pt":"Valor","tr":"Değer"},"type":"number","unit":"count"},{"key":"unit","label":{"ar":"الوحدة","de":"Einheit","en":"Unit","es":"Unidad","fr":"Unité","pt":"Unidade","tr":"Birim"},"language":"en","type":"text"}],"description":{"ar":"نطاق مجموعة البيانات التي أعدها الباحثون لتدريب النموذج وتقييمه.","de":"Umfang des für Training und Bewertung erstellten Datensatzes.","en":"Scope of the dataset assembled by the researchers for model training and evaluation.","es":"Alcance del conjunto creado para entrenar y evaluar el modelo.","fr":"Périmètre du jeu de données créé pour entraîner et évaluer le modèle.","pt":"Âmbito do conjunto criado para treinar e avaliar o modelo.","tr":"Araştırmacıların model eğitimi ve değerlendirmesi için oluşturduğu veri kümesinin kapsamı."},"id":"ground3d-lmm-dataset-summary","methodology":{"ar":"تصف هذه الأرقام الحجم والنطاق التقريبيين لمجموعة بيانات بحثية، ولا تمثل قياسات لأبوظبي أو الإمارات. وتُذكر نتيجة المقارنة التي تقارب 20% في ScanRefer بتحفظ، ولا ينبغي تفسيرها كأداء عام أو نتيجة ميدانية.","de":"Diese Angaben beschreiben den ungefähren Umfang eines Forschungsdatensatzes und sind keine Messwerte für Abu Dhabi oder die VAE. Der im Beitrag eingeordnete ScanRefer-Vergleich von knapp 20 Prozent ist kein allgemeiner Leistungs- oder Praxistest.","en":"These figures describe the approximate size and scope of a research dataset; they are not Abu Dhabi or UAE measurements. The reported near-20% ScanRefer comparison is qualified in the story and should not be interpreted as general performance or a field result.","es":"Estas cifras describen el tamaño y alcance aproximados de un conjunto de investigación; no son mediciones de Abu Dabi ni de los EAU. La comparación cercana al 20% en ScanRefer se presenta con la salvedad correspondiente y no equivale a rendimiento general ni a un resultado de campo.","fr":"Ces chiffres décrivent la taille et la portée approximatives d’un jeu de données de recherche ; ils ne mesurent ni Abou Dhabi ni les Émirats. Le résultat comparatif proche de 20 % sur ScanRefer est qualifié dans l’article et ne vaut pas mesure générale ou résultat de terrain.","pt":"Estes valores descrevem a dimensão e o âmbito aproximados de um conjunto de investigação, não medições de Abu Dhabi ou dos EAU. A comparação próxima de 20% no ScanRefer é contextualizada no artigo e não representa desempenho geral nem resultado no terreno.","tr":"Bunlar araştırma veri kümesinin yaklaşık hacim ve kapsam değerleridir; Abu Dabi veya BAE ölçümleri değildir. Modelin ScanRefer karşılaştırmasında bildirdiği yaklaşık üstünlük haber metninde nitelikli biçimde aktarılır; genel performans veya saha sonucu olarak yorumlanmamalıdır."},"rowTranslations":[{"label":{"ar":"أزواج أسئلة وأجوبة","de":"Frage-Antwort-Paare","en":"Question-answer pairs","es":"Pares de preguntas y respuestas","fr":"Paires de questions-réponses","pt":"Pares de perguntas e respostas","tr":"Soru-cevap çiftleri"},"unit":{"ar":"عدد","de":"Anzahl","en":"count","es":"cantidad","fr":"nombre","pt":"quantidade","tr":"adet"}},{"label":{"ar":"بيئات داخلية","de":"Innenraumumgebungen","en":"Indoor environments","es":"Entornos interiores","fr":"Environnements intérieurs","pt":"Ambientes internos","tr":"İç mekân ortamları"},"unit":{"ar":"عدد","de":"Anzahl","en":"count","es":"cantidad","fr":"nombre","pt":"quantidade","tr":"adet"}},{"label":{"ar":"مهام","de":"Aufgaben","en":"Tasks","es":"Tareas","fr":"Tâches","pt":"Tarefas","tr":"Görevler"},"unit":{"ar":"عدد","de":"Anzahl","en":"count","es":"cantidad","fr":"nombre","pt":"quantidade","tr":"adet"}}],"rows":[{"label":"Question-answer pairs","unit":"count","value":2500000},{"label":"Indoor environments","unit":"count","value":2500},{"label":"Tasks","unit":"count","value":8}],"sourceUrls":["https://mbzuai.ac.ae/news-events/news/building-llm-can-reason-about-the-physical-3d-world-fine-grained-level"],"title":{"ar":"ملخص مجموعة بيانات Ground3D-LMM","de":"Zusammenfassung des Ground3D-LMM-Datensatzes","en":"Ground3D-LMM dataset summary","es":"Resumen del conjunto Ground3D-LMM","fr":"Résumé du jeu de données Ground3D-LMM","pt":"Resumo do conjunto de dados Ground3D-LMM","tr":"Ground3D-LMM veri seti özeti"},"type":"table","updatedAt":"2026-10-20T14:12:00Z"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026/data/ground3d-lmm-dataset-summary?lang=es&format=csv","json":"https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026/data/ground3d-lmm-dataset-summary?lang=es&format=json"},"id":"ground3d-lmm-dataset-summary"}],"data_types":["table"],"editorial_illustration":{"alt":"Ilustración conceptual de tecnología, procesadores e información conectada.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"es","scope":"topic","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"event_id":"event-9a32d995-6ff4-575d-bf23-56a30db992a3","event_period":"2026-10-20","event_period_basis":"event-or-reference-period","id":"mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026","image":null,"importance":0.6,"language":"es","modified_at":"2026-10-20T14:20:10+00:00","publication_basis":"publication-record","published_at":"2026-10-20T14:20:10+00:00","reading_minutes":1,"region":"world","relations":[],"section_illustration":{"alt":"Ilustración conceptual de tecnología, procesadores e información conectada.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"es","scope":"section","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"slug":"mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026","sources":[{"checkedAt":"2026-10-20","name":"Mohamed bin Zayed University of Artificial Intelligence","publishedAt":"2026-10-20","url":"https://mbzuai.ac.ae/news-events/news/building-llm-can-reason-about-the-physical-3d-world-fine-grained-level"}],"summary":"Ground3D-LMM de MBZUAI relaciona texto con nubes de puntos 3D para localizar y medir objetos y sus partes.","text":"Ground3D-LMM de MBZUAI relaciona texto con nubes de puntos 3D para localizar y medir objetos y sus partes.\n\nGround3D-LMM, desarrollado por investigadores de MBZUAI, combina instrucciones de texto con nubes de puntos 3D para localizar y medir objetos y partes concretas de una escena. Según una nota de la universidad del 20 de octubre, el modelo se entrenó y evaluó con un conjunto de datos creado a partir de ScanNet y ScanNet++, con anotaciones de objetos y sus partes.\n\nEl conjunto contiene unos 2,5 millones de pares de preguntas y respuestas, alrededor de 2.500 entornos interiores y ocho tareas. MBZUAI informó que Ground3D-LMM superó a otros sistemas por cerca del 20% en ScanRefer sin usar imágenes 2D; es un resultado comparativo en una prueba de investigación específica. Los resultados se presentaron en ECCV 2026. El estudio no demuestra capacidad robótica en el mundo real ni mediciones físicas fiables.","title":"Investigadores de MBZUAI presentan un modelo lingüístico 3D de localización detallada","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026"},{"api_url":"https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026?lang=en","language":"en","url":"https://newsverum.com/en/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026"},{"api_url":"https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026"},{"api_url":"https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026"},{"api_url":"https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026?lang=es","language":"es","url":"https://newsverum.com/es/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026"},{"api_url":"https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026?lang=de","language":"de","url":"https://newsverum.com/de/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026"},{"api_url":"https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026"}],"url":"https://newsverum.com/es/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026"},"version":"1"}