PolyU-Led Survey Maps Human-Centric AI: 3 Perspectives, 6 Layers from Body Perception to Embodied Agents
机器之心 · wechat · 2026-09-06
A team led by Prof. Guo Jingcai (Hong Kong PolyU), with PKU, Tongji, RIKEN AIP, Alibaba and others, published a survey 'Human-Centric Intelligence in the Era of Foundation Models' proposing a full-spectrum framework of 3 perspectives and 6 layers, plus a continuously updated GitHub resource hub.\n\nThe framework expands by representation scope: observable subject covers human visual perception/generation, 3D reconstruction, parametric body modeling and animatable avatars; dynamic actor covers motion generation/understanding, human-centric audio-video generation, and human-object-scene interaction modeling; situated agent covers human-conditioned world models and humanoid embodied action, transferring human video experience into generalizable control.\n\nIt organizes datasets/benchmarks into body, dynamics, interaction, and embodiment categories, and outlines six challenges: trustworthy scalable human data, cross-layer foundation models, physically consistent body dynamics, human-centric world models, comprehensive evaluation protocols, and deployable systems — moving from 'looks plausible' to structurally credible, physically valid, and actionably useful.
More from Embodied
- HKU's TILDE Distills Embodied Foundation Models into Robot Policies — hkuhk · 2026-10-23
- 10 of 12 Beta Robots Worked Without Fine-Tuning — Do We Still Need It? — micoolcho · 2026-10-23
- EmbodiedEvo lets robot agents self-train, banking reusable Skills and Lessons across tasks — jiqizhixin · 2026-10-23
- KAIST's FRED lifts robot policy success from 19.4% to 50% via self-distilled future video representations — kaist-ai · 2026-10-23
- GALAX Launches World's First RTX 5080 With Dual 12V-2x6 Connectors at $3000 — chemist_slime · 2026-10-23
- Figure prints 81 minutes of robot data per second, spent ~$8.1M on data last week — joecole · 2026-10-23