[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"ai-news-lumia-lab-scales-latent-space-model-to-89-billion-parameters-en":3,"ai-news-more-lumia-lab-scales-latent-space-model-to-89-billion-parameters-en":45},{"snack":4,"alternates":30},{"headline":5,"tldr":6,"whyItMatters":7,"keyPoints":8,"source":12,"relatedSolutions":15,"topic":18,"schemaOrg":19,"generatedAt":22,"imageConcept":27,"coverImage":28,"publishedAt":29},"Lumia Lab scales latent space model to 8.9 billion parameters","LUMIA Lab has released the technical report for NCP-ArchPreview, an 8.9B parameter model trained on 5.73 trillion tokens. The model employs Next Concept Prediction to jointly predict tokens and latent representations, achieving performance parity with OLMo-3-7B while requiring significantly less data.","This research demonstrates that latent-space modelling can significantly improve training efficiency for large scale models. For enterprise teams, this suggests a path toward high performance systems with reduced computational overhead and smaller dataset requirements.",[9,10,11],"Scales Next Concept Prediction to 8.9B parameters using the Dolma-3 dataset","Matches the performance of OLMo-3-7B using only 51 percent of the training tokens","Integrates token and latent representation prediction for enhanced semantic understanding",{"name":13,"url":14},"bing news","https://aiweekly.co/alerts/ncp-archpreview-lumia-lab-trains-89b-latent-space-lm-that-matches-olmo-3-7b-on",[16,17],"/solutions/capabilities/generative-ai","/solutions/capabilities/machine-learning","models",{"@type":20,"headline":5,"description":6,"inLanguage":21,"datePublished":22,"dateModified":22,"author":23,"publisher":26,"isBasedOn":14},"NewsArticle","en","2026-09-11T04:03:45.707Z",{"@type":24,"name":25},"Organization","SevenLab",{"@type":24,"name":25},"A large glowing sphere of interconnected nodes representing a complex neural network in a dark laboratory","news-lumia-lab-scales-latent-space-model-to-89-billion-parameters.webp","2026-09-11T04:04:20.381Z",[31,34,36,39,42],{"locale":32,"slug":33},"de","lumia-lab-skaliert-latent-space-modell-auf-89-milliarden-parameter",{"locale":21,"slug":35},"lumia-lab-scales-latent-space-model-to-89-billion-parameters",{"locale":37,"slug":38},"es","lumia-lab-escala-el-modelo-de-espacio-latente-a-89-mil-millones-de-parametros",{"locale":40,"slug":41},"fr","lumia-lab-porte-son-modele-despace-latent-a-89-milliards-de-parametres",{"locale":43,"slug":44},"nl","lumia-lab-schaalt-latent-space-model-op-naar-89-miljard-parameters",{"items":46,"page":80,"hasMore":81},[47,54,60,66,73,79],{"slug":48,"headline":49,"summary":50,"topic":51,"sourceName":13,"publishedAt":52,"coverImage":53},"anthropic-chief-executive-calls-for-slower-pace-in-artificial-intelligence-development","Anthropic chief executive calls for slower pace in artificial intelligence development","Dario Amodei, the chief executive of Anthropic, has publicly advocated for a reduction in the speed of artificial intelligence development to prioritise safety and security. His concerns regarding the potential for large scale risks are shared by other prominent industry figures including Sam Altman and Elon Musk.","research","2026-09-13T04:03:01.105Z","news-anthropic-chief-executive-calls-for-slower-pace-in-artificial-intelligence-development.webp",{"slug":55,"headline":56,"summary":57,"topic":18,"sourceName":13,"publishedAt":58,"coverImage":59},"world-labs-launches-atlas-to-move-ai-from-language-to-spatial-world-models","World Labs launches Atlas to move AI from language to spatial world models","World Labs has introduced Atlas, a spatial intelligence model designed to move beyond text based processing. Unlike traditional large language models, this system focuses on creating world models that comprehend and interact with 3D physical spaces. The technology provides AI with a foundational understanding of depth, physics, and spatial relationships.","2026-09-13T04:02:14.465Z","news-world-labs-launches-atlas-to-move-ai-from-language-to-spatial-world-models.webp",{"slug":61,"headline":62,"summary":63,"topic":18,"sourceName":13,"publishedAt":64,"coverImage":65},"modern-cisos-shift-focus-to-enable-strategic-risk-and-accelerate-ai-adoption","Modern CISOs shift focus to enable strategic risk and accelerate AI adoption","Security leadership is moving away from a traditional gatekeeper role to become an active enabler of business risk and innovation. This transition focuses on guiding the safe integration of artificial intelligence while fostering a culture of responsible experimentation across the enterprise.","2026-09-12T04:03:58.890Z","news-modern-cisos-shift-focus-to-enable-strategic-risk-and-accelerate-ai-adoption.webp",{"slug":67,"headline":68,"summary":69,"topic":70,"sourceName":13,"publishedAt":71,"coverImage":72},"equinix-expands-ai-infrastructure-role-through-deepened-nvidia-partnership","Equinix expands AI infrastructure role through deepened Nvidia partnership","Equinix is leveraging its legacy data centre footprint to provide specialised colocation services for AI workloads. By deepening its partnership with Nvidia, the company offers enterprises managed private clouds for high performance computing.","tooling","2026-09-12T04:03:06.866Z","news-equinix-expands-ai-infrastructure-role-through-deepened-nvidia-partnership.webp",{"slug":74,"headline":75,"summary":76,"topic":18,"sourceName":13,"publishedAt":77,"coverImage":78},"tech-coalition-urges-us-government-to-protect-open-weight-ai-models","Tech coalition urges US government to protect open-weight AI models","A coalition of major technology firms has petitioned the US government to safeguard the development of open-weight artificial intelligence models. The group argues that downloadable weights are essential for maintaining transparency and competition, ensuring that innovation is not restricted to a handful of proprietary providers.","2026-09-12T04:02:20.002Z","news-tech-coalition-urges-us-government-to-protect-open-weight-ai-models.webp",{"slug":35,"headline":5,"summary":6,"topic":18,"sourceName":13,"publishedAt":29,"coverImage":28},1,true]