--- title: Nvidia’s new DNA model learns what token prediction misses description: Nvidia has released JEPA-DNA on Hugging Face, a genomic foundation model that combines masked language modeling (MLM) with a latent-space prediction objective... canonical: https://daily.dev/posts/nvidia-s-new-dna-model-learns-what-token-prediction-misses-18bymmrtc twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Nvidia’s new DNA model learns what token prediction misses | daily.dev og:description: Nvidia has released JEPA-DNA on Hugging Face, a genomic foundation model that combines masked language modeling (MLM) with a latent-space prediction objective... og:url: https://daily.dev/posts/nvidia-s-new-dna-model-learns-what-token-prediction-misses-18bymmrtc og:image: https://api.daily.dev/og/posts/18bymMrtC.png og:image:alt: Nvidia’s new DNA model learns what token prediction misses og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Nvidia’s new DNA model learns what token prediction misses **[The New Stack](https://daily.dev/sources/newstack)** · 3 min read · 0 upvotes · 0 comments ## Summary Nvidia has released JEPA-DNA on Hugging Face, a genomic foundation model that combines masked language modeling (MLM) with a latent-space prediction objective inspired by Yann LeCun's JEPA architecture. Unlike conventional genomic models that rely solely on token reconstruction, JEPA-DNA also supervises the model's global sequence embedding in latent space, enabling it to capture broader functional meaning of DNA sequences rather than just local syntax. Built on top of DNABERT-2 (117M parameters), the model is available for non-commercial research and supports tasks like feature extraction, linear probing, continual pre-training, and zero-shot scoring of DNA sequence changes. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#ai](https://daily.dev/tags/ai), [#nvidia](https://daily.dev/tags/nvidia) [View this post on daily.dev](https://daily.dev/posts/nvidia-s-new-dna-model-learns-what-token-prediction-misses-18bymmrtc) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Nvidia’s new DNA model learns what token prediction misses","url":"https://daily.dev/posts/nvidia-s-new-dna-model-learns-what-token-prediction-misses-18bymmrtc","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/nvidia-s-new-dna-model-learns-what-token-prediction-misses-18bymmrtc"},"datePublished":"2026-07-23T18:49:47.403Z","dateModified":"2026-07-23T20:07:55.776Z","description":"Nvidia has released JEPA-DNA on Hugging Face, a genomic foundation model that combines masked language modeling (MLM) with a latent-space prediction objective...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/ced19d13997eff9c125a20f60d0ae28d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/ced19d13997eff9c125a20f60d0ae28d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/nvidia-s-new-dna-model-learns-what-token-prediction-misses-18bymmrtc","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,nvidia","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"Nvidia’s new DNA model learns what token prediction misses"}]} ```