{"article":{"annotation":{"article_id":"nvidia-nemotron-35-super-vl-multimodal-agent-model","available_at":"2026-10-15T20:20:14.461365Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"b3f5d43a038b10a70a46066de2193b6610e6f41156ac185f937e4c89e6bc8cf4","input_sha256":"dd8867755d9cb5060efb9d63113e342bf01dd526aa3100b26c3798f1abdc0c16","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":"US","evidence":[{"field":"country","language":"en","note":"Explicit preserved editorial country/region; no city or national centroid inferred","source_urls":["https://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/"]}],"geometry":null,"id":"iso3166-1:US","kind":"country-or-area","labels":{"ar":"الولايات المتحدة الأمريكية","en":"United States of America","es":"Estados Unidos de América","fr":"États-Unis d’Amérique"},"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://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/"]}],"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/nvidia-nemotron-35-super-vl-multimodal-agent-model?lang=fr","category":"technology","content":{"key_points":[],"paragraphs":["NVIDIA a présenté le 15 octobre Nemotron 3.5 Super VL, un modèle multimodal ouvert et personnalisable. Son article technique décrit une architecture à mélange d’experts de 120 milliards de paramètres, dont 12 milliards sont activés par jeton, qui associe compréhension visuelle et textuelle, raisonnement et outils.","L’entreprise a déclaré un débit jusqu’à cinq fois supérieur à celui d’autres modèles ouverts de taille comparable sur des tâches d’agents avec un seul GPU. NVIDIA a également partagé des résultats de clients ayant adapté le modèle à des flux spécialisés. Ce sont des comparaisons et résultats déclarés par l’entreprise, sans mesure indépendante dans un test commun."],"sections":[]},"corrections":[],"country":"US","data":{"blocks":[{"description":{"ar":"أعلنت NVIDIA نموذجاً مفتوحاً يجمع فهم النص والصورة والوثائق والفيديو مع الاستدلال واستخدام الأدوات.","de":"NVIDIA kündigte ein offenes Modell an, das Text, Bilder, Dokumente und Video mit Schlussfolgern und Werkzeugen verbindet.","en":"NVIDIA announced an open model combining text, image, document and video understanding with reasoning and tool use.","es":"NVIDIA anunció un modelo abierto que combina texto, imágenes, documentos y vídeo con razonamiento y herramientas.","fr":"NVIDIA a annoncé un modèle ouvert associant texte, images, documents et vidéos au raisonnement et aux outils.","pt":"A NVIDIA anunciou um modelo aberto que combina texto, imagens, documentos e vídeo com raciocínio e ferramentas.","tr":"NVIDIA, metin, görüntü, belge ve videoyu akıl yürütme ve araç kullanımıyla birleştiren açık bir model duyurdu."},"id":"nvidia-nemotron-35-super-vl-multimodal-agent-model-release","items":[{"date":"2026-10-15","description":{"ar":"أعلنت NVIDIA نموذجاً مفتوحاً يجمع فهم النص والصورة والوثائق والفيديو مع الاستدلال واستخدام الأدوات.","de":"NVIDIA kündigte ein offenes Modell an, das Text, Bilder, Dokumente und Video mit Schlussfolgern und Werkzeugen verbindet.","en":"NVIDIA announced an open model combining text, image, document and video understanding with reasoning and tool use.","es":"NVIDIA anunció un modelo abierto que combina texto, imágenes, documentos y vídeo con razonamiento y herramientas.","fr":"NVIDIA a annoncé un modèle ouvert associant texte, images, documents et vidéos au raisonnement et aux outils.","pt":"A NVIDIA anunciou um modelo aberto que combina texto, imagens, documentos e vídeo com raciocínio e ferramentas.","tr":"NVIDIA, metin, görüntü, belge ve videoyu akıl yürütme ve araç kullanımıyla birleştiren açık bir model duyurdu."},"label":{"ar":"أعلنت NVIDIA عن Nemotron 3.5 Super VL للوكلاء متعددي الوسائط","de":"NVIDIA stellt Nemotron 3.5 Super VL für multimodale Agenten vor","en":"NVIDIA introduces Nemotron 3.5 Super VL for multimodal agents","es":"NVIDIA presenta Nemotron 3.5 Super VL para agentes multimodales","fr":"NVIDIA présente Nemotron 3.5 Super VL pour les agents multimodaux","pt":"A NVIDIA apresenta Nemotron 3.5 Super VL para agentes multimodais","tr":"NVIDIA, çok modlu ajanlar için Nemotron 3.5 Super VL modelini tanıttı"},"status":"occurred"}],"methodology":{"ar":"يلخص هذا السجل المنظم الإعلان المذكور؛ ولا يمثل تحققاً مستقلاً من الأداء.","de":"Dieser Eintrag fasst die genannte Ankündigung zusammen; er ist keine unabhängige Leistungsbewertung.","en":"This structured record summarizes the cited announcement; it is not an independent performance evaluation.","es":"Este registro resume el anuncio citado; no es una evaluación independiente del rendimiento.","fr":"Cette fiche résume l’annonce citée ; elle ne constitue pas une évaluation indépendante des performances.","pt":"Este registo resume o anúncio citado; não é uma avaliação independente do desempenho.","tr":"Bu yapılandırılmış kayıt, belirtilen duyuruyu özetler; bağımsız performans doğrulaması değildir."},"sourceUrls":["https://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/"],"title":{"ar":"أعلنت NVIDIA عن Nemotron 3.5 Super VL للوكلاء متعددي الوسائط","de":"NVIDIA stellt Nemotron 3.5 Super VL für multimodale Agenten vor","en":"NVIDIA introduces Nemotron 3.5 Super VL for multimodal agents","es":"NVIDIA presenta Nemotron 3.5 Super VL para agentes multimodales","fr":"NVIDIA présente Nemotron 3.5 Super VL pour les agents multimodaux","pt":"A NVIDIA apresenta Nemotron 3.5 Super VL para agentes multimodais","tr":"NVIDIA, çok modlu ajanlar için Nemotron 3.5 Super VL modelini tanıttı"},"type":"events","updatedAt":"2026-10-15T20:11:11Z"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/nvidia-nemotron-35-super-vl-multimodal-agent-model/data/nvidia-nemotron-35-super-vl-multimodal-agent-model-release?lang=fr&format=csv","json":"https://newsverum.com/api/v1/articles/nvidia-nemotron-35-super-vl-multimodal-agent-model/data/nvidia-nemotron-35-super-vl-multimodal-agent-model-release?lang=fr&format=json"},"id":"nvidia-nemotron-35-super-vl-multimodal-agent-model-release"}],"data_types":["events"],"editorial_illustration":{"alt":"Illustration conceptuelle de la technologie, des processeurs et des informations connectées.","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":"fr","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-f99efa29-f0c5-5632-b8ee-c5e47a8c5f0e","event_period":"2026-10-15","event_period_basis":"event-or-reference-period","id":"nvidia-nemotron-35-super-vl-multimodal-agent-model","image":null,"importance":0.6,"language":"fr","modified_at":"2026-10-15T20:19:53+00:00","publication_basis":"publication-record","published_at":"2026-10-15T20:19:53+00:00","reading_minutes":1,"region":"world","section_illustration":{"alt":"Illustration conceptuelle de la technologie, des processeurs et des informations connectées.","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":"fr","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":"nvidia-nemotron-35-super-vl-multimodal-agent-model","sources":[{"checkedAt":"2026-10-15","name":"NVIDIA Technical Blog","publishedAt":"2026-10-15","url":"https://developer.nvidia.com/blog/nvidia-nemotron-3-5-super-vl-powers-specialized-agents-with-multimodal-reasoning/"}],"summary":"NVIDIA a annoncé un modèle ouvert associant texte, images, documents et vidéos au raisonnement et aux outils.","text":"NVIDIA a annoncé un modèle ouvert associant texte, images, documents et vidéos au raisonnement et aux outils.\n\nNVIDIA a présenté le 15 octobre Nemotron 3.5 Super VL, un modèle multimodal ouvert et personnalisable. Son article technique décrit une architecture à mélange d’experts de 120 milliards de paramètres, dont 12 milliards sont activés par jeton, qui associe compréhension visuelle et textuelle, raisonnement et outils.\n\nL’entreprise a déclaré un débit jusqu’à cinq fois supérieur à celui d’autres modèles ouverts de taille comparable sur des tâches d’agents avec un seul GPU. NVIDIA a également partagé des résultats de clients ayant adapté le modèle à des flux spécialisés. Ce sont des comparaisons et résultats déclarés par l’entreprise, sans mesure indépendante dans un test commun.","title":"NVIDIA présente Nemotron 3.5 Super VL pour les agents multimodaux","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/nvidia-nemotron-35-super-vl-multimodal-agent-model?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/nvidia-nemotron-35-super-vl-multimodal-agent-model"},{"api_url":"https://newsverum.com/api/v1/articles/nvidia-nemotron-35-super-vl-multimodal-agent-model?lang=en","language":"en","url":"https://newsverum.com/en/news/nvidia-nemotron-35-super-vl-multimodal-agent-model"},{"api_url":"https://newsverum.com/api/v1/articles/nvidia-nemotron-35-super-vl-multimodal-agent-model?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/nvidia-nemotron-35-super-vl-multimodal-agent-model"},{"api_url":"https://newsverum.com/api/v1/articles/nvidia-nemotron-35-super-vl-multimodal-agent-model?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/nvidia-nemotron-35-super-vl-multimodal-agent-model"},{"api_url":"https://newsverum.com/api/v1/articles/nvidia-nemotron-35-super-vl-multimodal-agent-model?lang=es","language":"es","url":"https://newsverum.com/es/news/nvidia-nemotron-35-super-vl-multimodal-agent-model"},{"api_url":"https://newsverum.com/api/v1/articles/nvidia-nemotron-35-super-vl-multimodal-agent-model?lang=de","language":"de","url":"https://newsverum.com/de/news/nvidia-nemotron-35-super-vl-multimodal-agent-model"},{"api_url":"https://newsverum.com/api/v1/articles/nvidia-nemotron-35-super-vl-multimodal-agent-model?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/nvidia-nemotron-35-super-vl-multimodal-agent-model"}],"url":"https://newsverum.com/fr/news/nvidia-nemotron-35-super-vl-multimodal-agent-model"},"version":"1"}