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
- NSF Launches $30M Center for Human and Robot Co-Adaptation Led by UT Austin — PeterStone_TX · 2026-09-06
- Musk says surgical robots will beat the world's best surgeon within 3 years — at scale — r0ck3t23 · 2026-09-06
- azr: Neuralink neural write access could one day enable 'text-to-LoRA' knowledge downloads for brains — beffjezos · 2026-09-06
- Roboticists' India Challenges on CNA, Plus AI Clip-Finder Demo — alysha_lobo · 2026-09-06
- Dev desperate for subvocalization mics to talk to AI agents, willing to write the software — cephaloform · 2026-09-06
- GPT-6 Astra robot turns washing machine button at 16x speed, still slow but effective — CyberRobooo · 2026-09-06