--- title: Researchers from Princeton and Meta AI Introduce ‘Lory’:... description: Researchers from Princeton and Meta AI introduce Lory, a fully-differentiable MoE model designed for autoregressive language model pre-training. Lory... canonical: https://daily.dev/posts/researchers-from-princeton-and-meta-ai-introduce-lory-a-fully-differentiable-moe-model-designed-f-qcrefh8v9 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Researchers from Princeton and Meta AI Introduce ‘Lory’: A Fully-Differentiable MoE Model Designed for Autoregressive Language Model Pre-Training | daily.dev og:description: Researchers from Princeton and Meta AI introduce Lory, a fully-differentiable MoE model designed for autoregressive language model pre-training. Lory... og:url: https://daily.dev/posts/researchers-from-princeton-and-meta-ai-introduce-lory-a-fully-differentiable-moe-model-designed-f-qcrefh8v9 og:image: https://api.daily.dev/og/posts/qCRefh8V9.png og:image:alt: Researchers from Princeton and Meta AI Introduce ‘Lory’: A Fully-Differentiable MoE Model Designed for Autoregressive Language Model Pre-Training 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. # Researchers from Princeton and Meta AI Introduce ‘Lory’: A Fully-Differentiable MoE Model Designed for Autoregressive Language Model Pre-Training **[Machine Learning News](https://daily.dev/sources/mlnews)** · 4 min read · 0 upvotes · 0 comments ## Summary Researchers from Princeton and Meta AI introduce Lory, a fully-differentiable MoE model designed for autoregressive language model pre-training. Lory outperforms dense models in language modeling and downstream tasks, and utilizes casual segment routing and similarity-based data batching techniques. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#mixture-of-experts](https://daily.dev/tags/mixture-of-experts) [View this post on daily.dev](https://daily.dev/posts/researchers-from-princeton-and-meta-ai-introduce-lory-a-fully-differentiable-moe-model-designed-f-qcrefh8v9) ```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":"Researchers from Princeton and Meta AI Introduce ‘Lory’: A Fully-Differentiable MoE Model Designed for Autoregressive Language Model Pre-Training","url":"https://daily.dev/posts/researchers-from-princeton-and-meta-ai-introduce-lory-a-fully-differentiable-moe-model-designed-f-qcrefh8v9","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/researchers-from-princeton-and-meta-ai-introduce-lory-a-fully-differentiable-moe-model-designed-f-qcrefh8v9"},"datePublished":"2024-05-12T17:20:58.908Z","dateModified":"2026-04-02T02:12:47.282Z","description":"Researchers from Princeton and Meta AI introduce Lory, a fully-differentiable MoE model designed for autoregressive language model pre-training. Lory...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3dbdf669e0e58216b18794d436654452?_a=AQAEuiZ","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3dbdf669e0e58216b18794d436654452?_a=AQAEuiZ","isAccessibleForFree":true,"articleSection":"Machine Learning News","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":"Machine Learning News","logo":"https://media.daily.dev/image/upload/s--0PoEtdkd--/f_auto/v1750409401/squads/marktechpost?_a=BAMClqZW0","url":"https://daily.dev/squads/mlnews"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/researchers-from-princeton-and-meta-ai-introduce-lory-a-fully-differentiable-moe-model-designed-f-qcrefh8v9","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"mixture-of-experts","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Machine Learning News","item":"https://daily.dev/squads/mlnews"},{"@type":"ListItem","position":3,"name":"Researchers from Princeton and Meta AI Introduce ‘Lory’: A Fully-Differentiable MoE Model Designed for Autoregressive Language Model Pre-Training"}]} ```