We are pleased to share <strong>Human-Centric Intelligence in the Era of Foundation Models: A Survey</strong>.</p>\n<p>This survey presents a full-spectrum view of human-centric intelligence through six interconnected context levels: visual appearance, spatial geometry, kinematic dynamics, interaction modeling, world simulation, and embodied agency. We systematically organize the methodological foundations, representative methods, datasets, benchmarks, evaluation metrics, and future directions of the field.</p>\n<p>We also maintain a continuously updated, community-driven collection of human-centric AI resources and warmly invite interested contributors to join us in expanding it.</p>\n<p>🌐 Project Page: <a href=\"https://cseeyangchen.github.io/Human-Centric-AI/homepage/\" rel=\"nofollow\">https://cseeyangchen.github.io/Human-Centric-AI/homepage/</a></p>\n<p>💻 GitHub Resources: <a href=\"https://github.com/cseeyangchen/Human-Centric-AI\" rel=\"nofollow\">https://github.com/cseeyangchen/Human-Centric-AI</a></p>\n","updatedAt":"2026-08-24T10:34:38.487Z","author":{"_id":"67e7ef7d80d26ca51d13e176","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/fw1Kbky2gbH6H5qPc58UW.png","fullname":"Yang Chen","name":"cseeychen","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8349462151527405},"editors":["cseeychen"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/fw1Kbky2gbH6H5qPc58UW.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.18184","authors":[{"_id":"6a8b9d273d26296ea30918aa","user":{"_id":"67e7ef7d80d26ca51d13e176","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/fw1Kbky2gbH6H5qPc58UW.png","isPro":false,"fullname":"Yang Chen","user":"cseeychen","type":"user","name":"cseeychen"},"name":"Yang Chen","status":"claimed_verified","statusLastChangedAt":"2026-08-24T08:12:20.442Z","hidden":false},{"_id":"6a8b9d273d26296ea30918ab","name":"Tianqi Wang","hidden":false},{"_id":"6a8b9d273d26296ea30918ac","name":"Xiaorui Jiang","hidden":false},{"_id":"6a8b9d273d26296ea30918ad","name":"Yilei Man","hidden":false},{"_id":"6a8b9d273d26296ea30918ae","name":"Yihua Shao","hidden":false},{"_id":"6a8b9d273d26296ea30918af","name":"Mengyuan Liu","hidden":false},{"_id":"6a8b9d273d26296ea30918b0","name":"Zhi Chen","hidden":false},{"_id":"6a8b9d273d26296ea30918b1","name":"Xiaofeng Cao","hidden":false},{"_id":"6a8b9d273d26296ea30918b2","name":"Qibin Zhao","hidden":false},{"_id":"6a8b9d273d26296ea30918b3","name":"Chi Harold Liu","hidden":false},{"_id":"6a8b9d273d26296ea30918b4","name":"Albert Y. Zomaya","hidden":false},{"_id":"6a8b9d273d26296ea30918b5","name":"Nicu Sebe","hidden":false},{"_id":"6a8b9d273d26296ea30918b6","name":"Jingren Zhou","hidden":false},{"_id":"6a8b9d273d26296ea30918b7","name":"Dacheng Tao","hidden":false},{"_id":"6a8b9d273d26296ea30918b8","name":"Song Guo","hidden":false},{"_id":"6a8b9d273d26296ea30918b9","name":"Jingcai Guo","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/67e7ef7d80d26ca51d13e176/pMPpEkTsZbCEwEt58Cs8B.png","https://cdn-uploads.huggingface.co/production/uploads/67e7ef7d80d26ca51d13e176/9NRa9lqzJEDkNfq8Ym3Em.png","https://cdn-uploads.huggingface.co/production/uploads/67e7ef7d80d26ca51d13e176/nOqhGzp_1Z-XhhXeV9iCG.png"],"publishedAt":"2026-08-18T00:00:00.000Z","submittedOnDailyAt":"2026-08-24T00:00:00.000Z","title":"Human-Centric Intelligence in the Era of Foundation Models: A Survey","submittedOnDailyBy":{"_id":"67e7ef7d80d26ca51d13e176","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/fw1Kbky2gbH6H5qPc58UW.png","isPro":false,"fullname":"Yang Chen","user":"cseeychen","type":"user","name":"cseeychen"},"summary":"Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling. Yet it has not fully integrated with foundation models to achieve the comparable progress seen in them. More importantly, recent advances across this broad landscape remain fragmented across tasks, modalities, and research communities, leaving their intrinsic conceptual and methodological connections unclear. To bridge these divides and rethink human-centric intelligence in the foundation-model era, we introduce a full-spectrum human context taxonomy that integrates six interconnected levels by viewing humans as observable subjects through visual appearance and spatial geometry, as dynamic actors through kinematic dynamics and interaction modeling, and as situated agents through world simulation and embodied agency. We next present the methodological foundations of the field, covering human-centric data families, computational architecture paradigms, and representative training and inference optimization strategies. We then systematically review representative methods across these levels and organize the associated datasets, benchmarks, and evaluation metrics. We further discuss open challenges and promising research directions toward human-centric intelligence that is scalable, trustworthy, physically grounded, and deployable, aiming to provide a coherent framework and practical reference for advancing the field. Finally, we provide a systematically organized and continuously updated collection of human-centric AI literature and resources on our project page.","upvotes":4,"discussionId":"6a8b9d273d26296ea30918ba","projectPage":"https://cseeyangchen.github.io/Human-Centric-AI/homepage/","githubRepo":"https://github.com/cseeyangchen/Human-Centric-AI","githubRepoAddedBy":"user","ai_summary":"This survey proposes a unified taxonomy and methodological framework for human-centric intelligence across visual, dynamic, and embodied levels within the foundation-model era.","ai_keywords":["foundation models","kinematic dynamics","interaction modeling","world simulation","embodied agency","computational architecture paradigms","training optimization","inference optimization"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":12},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"67e7ef7d80d26ca51d13e176","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/fw1Kbky2gbH6H5qPc58UW.png","isPro":false,"fullname":"Yang Chen","user":"cseeychen","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"6407e5294edf9f5c4fd32228","avatarUrl":"/avatars/8e2d55460e9fe9c426eb552baf4b2cb0.svg","isPro":false,"fullname":"Stoney Kang","user":"sikang99","type":"user"},{"_id":"620cb0582d8bc91e1cf2e6e6","avatarUrl":"/avatars/358ce8047869b1785ea2025eed7f72f2.svg","isPro":false,"fullname":"Zhihao Wu","user":"KunH","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.18184.md","query":{}}">
Human-Centric Intelligence in the Era of Foundation Models: A Survey
Abstract
This survey proposes a unified taxonomy and methodological framework for human-centric intelligence across visual, dynamic, and embodied levels within the foundation-model era.
Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling. Yet it has not fully integrated with foundation models to achieve the comparable progress seen in them. More importantly, recent advances across this broad landscape remain fragmented across tasks, modalities, and research communities, leaving their intrinsic conceptual and methodological connections unclear. To bridge these divides and rethink human-centric intelligence in the foundation-model era, we introduce a full-spectrum human context taxonomy that integrates six interconnected levels by viewing humans as observable subjects through visual appearance and spatial geometry, as dynamic actors through kinematic dynamics and interaction modeling, and as situated agents through world simulation and embodied agency. We next present the methodological foundations of the field, covering human-centric data families, computational architecture paradigms, and representative training and inference optimization strategies. We then systematically review representative methods across these levels and organize the associated datasets, benchmarks, and evaluation metrics. We further discuss open challenges and promising research directions toward human-centric intelligence that is scalable, trustworthy, physically grounded, and deployable, aiming to provide a coherent framework and practical reference for advancing the field. Finally, we provide a systematically organized and continuously updated collection of human-centric AI literature and resources on our project page.
Community
We are pleased to share Human-Centric Intelligence in the Era of Foundation Models: A Survey.
This survey presents a full-spectrum view of human-centric intelligence through six interconnected context levels: visual appearance, spatial geometry, kinematic dynamics, interaction modeling, world simulation, and embodied agency. We systematically organize the methodological foundations, representative methods, datasets, benchmarks, evaluation metrics, and future directions of the field.
We also maintain a continuously updated, community-driven collection of human-centric AI resources and warmly invite interested contributors to join us in expanding it.
🌐 Project Page: https://cseeyangchen.github.io/Human-Centric-AI/homepage/
💻 GitHub Resources: https://github.com/cseeyangchen/Human-Centric-AI
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2608.18184 in a model README.md to link it from this page.
Cite arxiv.org/abs/2608.18184 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2608.18184 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.