PolyU survey unifies fragmented human-centric AI research with a six-layer progressive framework
jiqizhixin · x · 2026-09-15
A Hong Kong Polytechnic University team led by Prof. Jingcai Guo releases a comprehensive survey arguing that human-centric AI research is fragmented across body attribute perception, 3D structure recovery, motion capture, human-object interaction reasoning, world dynamics prediction, and embodied experience transfer. The survey organizes the field into six progressively expanding layers: (1) perceiving/generating human visual attributes, (2) recovering/understanding human spatial structure, (3) capturing/generating human motion, (4) reasoning/generating human-environment interaction, (5) predicting human-centric world dynamics, and beyond — offering a unified conceptual modeling framework.
More from Research
- A 3-step learning path for tabular foundation models: book, code, TabArena — pandeyparul · 2026-09-15
- CoLLAs 2026 keynote: fix forgetting via drift compensation and model merging, not just prevention — apsarathchandar · 2026-09-15
- CoLLAs 2026 talk: accuracy metrics mislead lifelong learning evaluation, ground it in problem structure — apsarathchandar · 2026-09-15
- CoLLAs 2026: Michael Bowling challenges MDP foundations of continual reinforcement learning — apsarathchandar · 2026-09-15
- CoLLAs 2026 tutorial: make continual learning a design requirement, not an afterthought — apsarathchandar · 2026-09-15
- CoLLAs 2026 opens with tutorial bridging multi-agent RL and lifelong learning for non-stationarity — apsarathchandar · 2026-09-15