{
  "source_file": "0930",
  "source_platform": "研究机构",
  "author": "Meta AI Research",
  "title_listed": "Large Concept Models: Language Modeling in a Sentence Representation Space",
  "keywords": "大概念模型,LCM,表示",
  "domain": "大模型算法",
  "content_type": "深度技术解析",
  "is_paid_flag": "否",
  "url": "https://ai.meta.com/research/publications/large-concept-models-language-modeling-in-a-sentence-representation-space/",
  "publish_date": "2024-12",
  "corpus_stage": "预训练/SFT",
  "notes": "大概念模型：句子表示空间语言建模",
  "id": "65d8bc61332b",
  "collected_at": "2026-10-02T15:57:34",
  "title": "Large Concept Models: Language Modeling in a Sentence Representation Space | Research - AI at Meta",
  "body_markdown": "Products\nAI Research\nResources\nAbout\nAI Developers\nTry Muse\nNLP\nLarge Concept Models: Language Modeling in a Sentence Representation Space\nDecember 11, 2024\nAbstract\nLLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for\nmany tasks. The current established technology of LLMs is to process input and generate output at\nthe token level. This is in sharp contrast to humans who operate at multiple levels of abstraction, well\nbeyond single words, to analyze information and to generate creative content. In this paper, we present\nan attempt at an architecture which operates on an explicit higher-level semantic representation,\nwhich we name a “concept”. Concepts are language- and modality-agnostic and represent a higher\nlevel idea or action in a flow. Hence, we build a“Large Concept Model”. In this study, as\nproof of feasibility, we assume that a concept corresponds to a sentence, and use an existing sentence\nembedding space, SONAR, which supports up to 200 languages in both text and speech modalities.\nThe Large Concept Model is trained to perform autoregressive sentence prediction in an embedding\nspace. We explore multiple approaches, namely MSE regression, variants of diffusion-based generation,\nand models operating in a quantized SONAR space. These explorations are performed using 1.6B\nparameter models and training data in the order of 1.3T tokens. We then scale one architecture to a\nmodel size of 7B parameters and training data of about 7.7T tokens. We perform an experimental\nevaluation on several generative tasks, namely summarization and a new task of summary expansion.\nFinally, we show that our model exhibits impressive zero-shot generalization performance to many\nlanguages, outperforming existing LLMs of the same size. The training code of our models is freely\navailable.\nDownload the Paper\nAUTHORS\nWritten by\nThe LCM team\nLoic Barrault\nPaul-Ambroise Duquenne\nMaha Elbayad\nArtyom Kozhevnikov\nBelen Alastruey\nPierre Andrews\nMariano Coria\nGuillaume Couairon\nMarta R. Costa-jussa\nDavid Dale\nHady Elsahar\nKevin Heffernan\nJoão Maria Janeiro\nTuan Tran\nChristophe Ropers\nEduardo Sánchez\nRobin San Roman\nAlexandre Mourachko\nSafiyyah Saleem\nHolger Schwenk\nPublisher\narXiv\nResearch Topics\nNatural Language Processing (NLP)\nRelated Publications\nSeptember 24, 2026\nREINFORCEMENT LEARNING\nRESEARCH\nMaD-RL: Matching Distributions for Calibrating LLMs with Reinforcement Learning\nSourabh Kulkarni\n,\nKsheeraj Sai Vepuri\n,\nBasar Demir\n,\nJason Bohrer\n,\nEmily Shen\n,\nJianfa Chen\n,\nNan Jiang\n,\nAnkit Jain\n,\nHarihar Subramanyam\n,\nMannat Singh\n,\nChirag Nagpal\nSeptember 24, 2026\nRead the Paper\nJuly 29, 2026\nREINFORCEMENT LEARNING\nNLP\nReinforcement Learning for Code Optimization\nPierre Chambon\n,\nKunhao Zheng\n,\nJuliette Decugis\n,\nBenoît Sagot\n,\nGabriel Synnaeve\nJuly 29, 2026\nRead the Paper\nJuly 17, 2026\nCONVERSATIONAL AI\nREINFORCEMENT LEARNING\nLearning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning\nZilin Xiao\n,\nQi Ma\n,\nJason Chen\n,\nXintao Chen\n,\nAvinash Atreya\n,\nHanjie Chen\n,\nVicente Ordonez\nJuly 17, 2026\nRead the Paper\nJune 05, 2026\nCONVERSATIONAL AI\nRANKING AND RECOMMENDATIONS\nSuperintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval\nZeyu Yang\n,\nQi Ma\n,\nJason Chen\n,\nAnshumali Shrivastava\nJune 05, 2026\nRead the Paper\nSee All Papers\nHelp Us Pioneer The Future of AI\nWe share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.\nJoin our Team\nMeta AI\nAssistant\nMedia Generation\nVibes\nMuse\nAgent\nAI agents explained\nWhat is agentic AI\nAgentic AI examples\nAI Research\nOverview\nProjects\nResources & tools\nPublications\nGitHub\nResources\nBlog\nLearning Hub\nDemos\nAbout\nOverview\nOpen Source\nCareers\nMeta AI\nMeta AI\nAssistant\nMedia Generation\nVibes\nMuse\nMuse\nAgent\nAI agents explained\nWhat is agentic AI\nAgentic AI examples\nAI Research\nAI Research\nOverview\nProjects\nResources & tools\nPublications\nGitHub\nResources\nBlog\nLearning Hub\nDemos\nAbout\nAbout\nOverview\nOpen Source\nCareers\nPrivacy Policy\nTerms\nCookies\nMeta © 2026",
  "metadata": {
    "title": "Large Concept Models: Language Modeling in a Sentence Representation Space | Research - AI at Meta",
    "description": "LLMs have revolutionized the field of artificial intelligence and have emerged as the de-facto tool for\nmany tasks. The current established technology of...",
    "keywords": null,
    "author": null
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 200,
    "error": ""
  },
  "code_blocks": [],
  "images": [
    {
      "status": "ok",
      "url": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/252294889_575082167077436_6034106545912333281_n.svg/meta-logo-primary_standardsize.svg?_nc_cat=108&ccb=1-7&_nc_sid=e280be&_nc_ohc=hAHazKbORSwQ7kNvwFs3s3h&_nc_oc=AdpT8oey1lBbgzpbV7ZyVqYXvdIcHIx66czv3z4_y4D5VbmT8-LcxGwGhf3nCEqCFAg&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQNvb7eQiDrQ6_1LFGZYhEgNdXgDQIMGBb_9M8QERgfQcA&oe=6AD530B9",
      "bytes": 13990,
      "reused": false,
      "local_path": "attachments/65d8bc61332b/images/body-ad2e7120fa9565a6406b.svg",
      "src": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/252294889_575082167077436_6034106545912333281_n.svg/meta-logo-primary_standardsize.svg?_nc_cat=108&ccb=1-7&_nc_sid=e280be&_nc_ohc=hAHazKbORSwQ7kNvwFs3s3h&_nc_oc=AdpT8oey1lBbgzpbV7ZyVqYXvdIcHIx66czv3z4_y4D5VbmT8-LcxGwGhf3nCEqCFAg&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQNvb7eQiDrQ6_1LFGZYhEgNdXgDQIMGBb_9M8QERgfQcA&oe=6AD530B9",
      "alt": "Meta",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://scontent-dfw5-2.xx.fbcdn.net/v/t39.2365-6/90971213_248000486247635_8189447952712859648_n.jpg?_nc_cat=104&ccb=1-7&_nc_sid=e280be&_nc_ohc=54NmkRNvFEoQ7kNvwGOSvsh&_nc_oc=AdqKW5TQ_AvRltHCoTyvTJXJUOA-Jpuk8fodrH2dv88kvQItDNEEf0IcyCEOG86Qezw&_nc_zt=14&_nc_ht=scontent-dfw5-2.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQO_Q3IT3bMn1_RcKPwAvQfp6rOGzTrdaMTZEhLLvJjUOw&oe=6AE99497",
      "bytes": 351299,
      "reused": false,
      "local_path": "attachments/65d8bc61332b/images/body-91e8acac6e5fd73eea9b.jpg",
      "src": "https://scontent-dfw5-2.xx.fbcdn.net/v/t39.2365-6/90971213_248000486247635_8189447952712859648_n.jpg?_nc_cat=104&ccb=1-7&_nc_sid=e280be&_nc_ohc=54NmkRNvFEoQ7kNvwGOSvsh&_nc_oc=AdqKW5TQ_AvRltHCoTyvTJXJUOA-Jpuk8fodrH2dv88kvQItDNEEf0IcyCEOG86Qezw&_nc_zt=14&_nc_ht=scontent-dfw5-2.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQO_Q3IT3bMn1_RcKPwAvQfp6rOGzTrdaMTZEhLLvJjUOw&oe=6AE99497",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://scontent-dfw6-1.xx.fbcdn.net/v/t39.2365-6/87524316_2677189655726266_6338721200264445952_n.svg?_nc_cat=103&ccb=1-7&_nc_sid=e280be&_nc_ohc=fVw4LJojBokQ7kNvwGoeBzo&_nc_oc=AdrkP6I-04u6p4Jook2sPg73GEI1IfiIRn2GycI6WgIkObCoxv9tkmBFc09yToCgBiA&_nc_zt=14&_nc_ht=scontent-dfw6-1.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQM96sbpfZtiHo1kaeuFIBM3VX34EUHxI5PdxxswN1pq7A&oe=6AE99A78",
      "bytes": 768,
      "reused": false,
      "local_path": "attachments/65d8bc61332b/images/body-eebd7ee4c22b4a82fa9a.svg",
      "src": "https://scontent-dfw6-1.xx.fbcdn.net/v/t39.2365-6/87524316_2677189655726266_6338721200264445952_n.svg?_nc_cat=103&ccb=1-7&_nc_sid=e280be&_nc_ohc=fVw4LJojBokQ7kNvwGoeBzo&_nc_oc=AdrkP6I-04u6p4Jook2sPg73GEI1IfiIRn2GycI6WgIkObCoxv9tkmBFc09yToCgBiA&_nc_zt=14&_nc_ht=scontent-dfw6-1.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQM96sbpfZtiHo1kaeuFIBM3VX34EUHxI5PdxxswN1pq7A&oe=6AE99A78",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://scontent-dfw5-2.xx.fbcdn.net/v/t39.8562-6/335682312_964107378293184_3093631164486164913_n.svg?_nc_cat=100&ccb=1-7&_nc_sid=e280be&_nc_ohc=fYUd8cfKa3cQ7kNvwHzxyUo&_nc_oc=AdqO5CXvI_Ry9-R7gLxXAricVHfV9jgZI4bhWqxGsfabwKdJ_6gU1IS1JNw7Yk5A8rI&_nc_zt=14&_nc_ht=scontent-dfw5-2.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQNLVoIwHr2whkt55-wXitM_dZ6CCbuZA4KkCrWCVOdwqw&oe=6AD520E7",
      "bytes": 536,
      "reused": false,
      "local_path": "attachments/65d8bc61332b/images/body-2c433d54c1cafd79f0dd.svg",
      "src": "https://scontent-dfw5-2.xx.fbcdn.net/v/t39.8562-6/335682312_964107378293184_3093631164486164913_n.svg?_nc_cat=100&ccb=1-7&_nc_sid=e280be&_nc_ohc=fYUd8cfKa3cQ7kNvwHzxyUo&_nc_oc=AdqO5CXvI_Ry9-R7gLxXAricVHfV9jgZI4bhWqxGsfabwKdJ_6gU1IS1JNw7Yk5A8rI&_nc_zt=14&_nc_ht=scontent-dfw5-2.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQNLVoIwHr2whkt55-wXitM_dZ6CCbuZA4KkCrWCVOdwqw&oe=6AD520E7",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://scontent-dfw6-1.xx.fbcdn.net/v/t39.8562-6/336009607_1870102080040414_6753977241281150924_n.svg?_nc_cat=103&ccb=1-7&_nc_sid=e280be&_nc_ohc=EOxnus0Vys8Q7kNvwFGrms5&_nc_oc=AdodxvUHQnETZW32TOMmP5S_noQxTy-8rzUluvcvOmKo3rO2-NuuXTQLrgMGVVO-y84&_nc_zt=14&_nc_ht=scontent-dfw6-1.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQO2RSuFox1RZzTMeP2FV2Drly3qV7orOZL58q0zVQK-Qg&oe=6AD51922",
      "bytes": 1126,
      "reused": false,
      "local_path": "attachments/65d8bc61332b/images/body-cdda6514b70614b88077.svg",
      "src": "https://scontent-dfw6-1.xx.fbcdn.net/v/t39.8562-6/336009607_1870102080040414_6753977241281150924_n.svg?_nc_cat=103&ccb=1-7&_nc_sid=e280be&_nc_ohc=EOxnus0Vys8Q7kNvwFGrms5&_nc_oc=AdodxvUHQnETZW32TOMmP5S_noQxTy-8rzUluvcvOmKo3rO2-NuuXTQLrgMGVVO-y84&_nc_zt=14&_nc_ht=scontent-dfw6-1.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQO2RSuFox1RZzTMeP2FV2Drly3qV7orOZL58q0zVQK-Qg&oe=6AD51922",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/336289415_1541032296405649_2165099305308791297_n.svg?_nc_cat=109&ccb=1-7&_nc_sid=e280be&_nc_ohc=szNSkRClPB8Q7kNvwG_QuzC&_nc_oc=AdrwcmNZ6VBPiUuOKpS80tKMlMpN-566glDgJUkbOeVxfK_YcxcnHGmQXAT2VLrdJy4&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQOn2pvOHm3n8mEgcQO41tPzJJxwoVldhFRYXL3VR-iCsg&oe=6AD544FB",
      "bytes": 806,
      "reused": false,
      "local_path": "attachments/65d8bc61332b/images/body-41f6aecadc9385a32c2f.svg",
      "src": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/336289415_1541032296405649_2165099305308791297_n.svg?_nc_cat=109&ccb=1-7&_nc_sid=e280be&_nc_ohc=szNSkRClPB8Q7kNvwG_QuzC&_nc_oc=AdrwcmNZ6VBPiUuOKpS80tKMlMpN-566glDgJUkbOeVxfK_YcxcnHGmQXAT2VLrdJy4&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQOn2pvOHm3n8mEgcQO41tPzJJxwoVldhFRYXL3VR-iCsg&oe=6AD544FB",
      "alt": "",
      "downloaded": true
    },
    {
      "status": "ok",
      "url": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/335648731_142576991793348_7786819189843639239_n.svg?_nc_cat=108&ccb=1-7&_nc_sid=e280be&_nc_ohc=kR8jmDz5Tu8Q7kNvwFsKqaM&_nc_oc=AdqrOm2ElI15Ej13sM8SirbTVZiUpR5DMxc4KAJkrz9qH4EpZnouLCCNEJvPdLyTI_o&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQP6i9CXldJotaRK9MdmAxxoPcK1zgKKU4a1S656pRO4pw&oe=6AD5262E",
      "bytes": 771,
      "reused": false,
      "local_path": "attachments/65d8bc61332b/images/body-4e571c77605339f56712.svg",
      "src": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/335648731_142576991793348_7786819189843639239_n.svg?_nc_cat=108&ccb=1-7&_nc_sid=e280be&_nc_ohc=kR8jmDz5Tu8Q7kNvwFsKqaM&_nc_oc=AdqrOm2ElI15Ej13sM8SirbTVZiUpR5DMxc4KAJkrz9qH4EpZnouLCCNEJvPdLyTI_o&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQP6i9CXldJotaRK9MdmAxxoPcK1zgKKU4a1S656pRO4pw&oe=6AD5262E",
      "alt": "",
      "downloaded": true
    }
  ],
  "audio": [],
  "videos": [
    {
      "url": "https://www.youtube.com/@aiatmeta",
      "src": "https://www.youtube.com/@aiatmeta",
      "status": "reference_only",
      "kind": "channel_reference"
    }
  ],
  "links": [
    {
      "href": "https://developer.meta.com/ai/?utm_source=ai_meta_site&utm_medium=web&utm_campaign=nav_AI-developers_07242026&utm_content=nav_AI-developers",
      "label": "AI Developers",
      "type": "a"
    },
    {
      "href": "https://applink.muse.ai/?pt=10684&pid=ai_meta_site&utm_source=ai_meta_site&utm_medium=web&utm_campaign=nav_try-muse_09082026&utm_content=nav_try-muse_09082026&ct=nav_try-muse_09082026&referrer=utm_source%3Dai_meta_site%26utm_medium%3Dweb%26utm_campaign%3Dnav_try-muse_09082026%26utm_content%3Dnav_try-muse_09082026",
      "label": "Try Muse",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://scontent-dfw6-1.xx.fbcdn.net/v/t39.2365-6/470149925_936340665123313_5359535905316748287_n.pdf?_nc_cat=103&ccb=1-7&_nc_sid=3c67a6&_nc_ohc=-ah8Lbjz2DwQ7kNvwGaHtF1&_nc_oc=AdpsfsQtgJZPDsiAo4GA2rlT7KB86wA1Qxa611ZR_KwzfeeWqZEbKQLXP5LgvWJCCts&_nc_zt=14&_nc_ht=scontent-dfw6-1.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQMnQzbEeHrVFlvWafD3gUoj1YYDxywkcq2qy6wSEpQWYg&oe=6AD53792",
      "label": "Download the Paper",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/people/1679073599776654/loic-barrault/",
      "label": "Loic Barrault",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/people/875226594354961/maha-elbayad/",
      "label": "Maha Elbayad",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/people/271799079300984/holger-schwenk/",
      "label": "Holger Schwenk",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/research/nlp/",
      "label": "Natural Language Processing (NLP)",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/research/publications/mad-rl-matching-distributions-for-calibrating-llms-with-reinforcement-learning/",
      "label": "Read the Paper",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/research/publications/reinforcement-learning-for-code-optimization/",
      "label": "Read the Paper",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/people/1040815388353877/zilin-xiao/",
      "label": "Zilin Xiao",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/research/publications/learning-to-reason-by-analogy-via-retrieval-augmented-reinforcement-fine-tuning/",
      "label": "Read the Paper",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/research/publications/superintelligent-retrieval-agent-the-next-frontier-of-agentic-retrieval/",
      "label": "Read the Paper",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/global_search/?content_types%5B0%5D=publication&page=1",
      "label": "See All Papers",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/join-us/",
      "label": "Join our Team",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/meta-ai/assistant/",
      "label": "Meta AI",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/meta-ai/media-generation/",
      "label": "Media Generation",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/meta-ai/vibes/",
      "label": "Vibes",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/muse/",
      "label": "Muse",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/learn/agentic-ai/what-are-ai-agents/",
      "label": "AI agents explained",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/learn/agentic-ai/what-is-agentic-ai/",
      "label": "What is agentic AI",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/learn/agentic-ai/agentic-ai-examples/",
      "label": "Agentic AI examples",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/research",
      "label": "AI Research",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/research/",
      "label": "Overview",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/resources/",
      "label": "Resources & tools",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/results/?content_types%5B0%5D=publication",
      "label": "Publications",
      "type": "a"
    },
    {
      "href": "https://github.com/facebookresearch/",
      "label": "GitHub",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/blog/",
      "label": "Blog",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/learn/",
      "label": "Learning Hub",
      "type": "a"
    },
    {
      "href": "https://aidemos.meta.com/",
      "label": "Demos",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/about",
      "label": "About",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/about/",
      "label": "Overview",
      "type": "a"
    },
    {
      "href": "https://ai.meta.com/opensourceai/",
      "label": "Open Source",
      "type": "a"
    },
    {
      "href": "https://www.metacareers.com/jobs/?is_leadership=0&sub_teams[0]=Artificial%20Intelligence&is_in_page=0",
      "label": "Careers",
      "type": "a"
    },
    {
      "href": "https://www.facebook.com/aiatmeta/",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://twitter.com/aiatmeta/",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://www.linkedin.com/showcase/aiatmeta",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://www.youtube.com/@aiatmeta",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://www.facebook.com/about/privacy/",
      "label": "Privacy Policy",
      "type": "a"
    },
    {
      "href": "https://www.facebook.com/policies/",
      "label": "Terms",
      "type": "a"
    },
    {
      "href": "https://www.facebook.com/policies/cookies/",
      "label": "Cookies",
      "type": "a"
    }
  ],
  "repair_version": 2,
  "repaired_at": "2026-10-14T10:53:42Z",
  "source_url": "https://ai.meta.com/research/publications/large-concept-models-language-modeling-in-a-sentence-representation-space/",
  "papers": [
    {
      "status": "ok",
      "url": "https://scontent-dfw6-1.xx.fbcdn.net/v/t39.2365-6/470149925_936340665123313_5359535905316748287_n.pdf?_nc_cat=103&ccb=1-7&_nc_sid=3c67a6&_nc_ohc=-ah8Lbjz2DwQ7kNvwGaHtF1&_nc_oc=AdpsfsQtgJZPDsiAo4GA2rlT7KB86wA1Qxa611ZR_KwzfeeWqZEbKQLXP5LgvWJCCts&_nc_zt=14&_nc_ht=scontent-dfw6-1.xx&_nc_gid=etgEZo_oZSdl-moyuuexTg&_nc_ss=7820f&oh=00_AQMnQzbEeHrVFlvWafD3gUoj1YYDxywkcq2qy6wSEpQWYg&oe=6AD53792",
      "bytes": 1597254,
      "reused": false,
      "local_path": "papers/repair/8595f642d27e0a21f2fd.pdf"
    }
  ],
  "actual_video_files": [],
  "body_chars": 4098,
  "expected_body_images": 7,
  "discovery_status": "ok",
  "delivery_status": "ok",
  "missing_reason": "",
  "raw_html": "attachments/65d8bc61332b/pages/source.html",
  "local_html": "attachments/65d8bc61332b/pages/article.html",
  "body_base_path": "attachments/65d8bc61332b/pages/",
  "body_markdown_path": "attachments/65d8bc61332b/pages/article.md"
}