He Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
He Zhang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Hui Xiong
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and The Hong Kong University of Science and Technology, Hong Kong SAR, China
2 shared publications - Haonan Lu
OPPO AI Center OPPO AI Center OPPO AI Center OPPO AI Center Tsinghua University
1 shared publication - Jiacheng Qian
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China, China
1 shared publication - Qianyi Cai
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China, China
1 shared publication - Weiyu Guo
Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
1 shared publication - Xiaodong Lin
Rutgers University, New Brunswick, NJ, USA
1 shared publication
Latest Publications
- Open Access
- 15 October 2026
- Published by MDPI AG in Preprints.org
Behavioral Organization in Embodied AI: A Three-Level Survey
Recent years have witnessed a rapid proliferation of learning, control, and planning algorithms for embodied AI. However, grouping methods by model family or learning paradigm often separates approaches serving the same behavioral function, hindering comparison. To address this gap, this survey classifies robotic manipulation research into three functional levels: sensorimotor behavior, reusable units, and task organization. This functional perspective brings together reinforcement learning approaches, vision-language-action models, world models, and code-as-policy methods. The taxonomy supports comparison within functional categories and the transfer of ideas across approaches, offering insights for future algorithm development toward more adaptable embodied systems.
- 15 October 2026
- Published by MDPI AG in Preprints.org
Open AccessBehavioral Organization in Embodied AI: A Three-Level Survey
Recent years have witnessed a rapid proliferation of learning, control, and planning algorithms for embodied AI. However, grouping methods by model family or learning paradigm often separates approaches serving the same behavioral function, hindering comparison. To address this gap, this survey classifies robotic manipulation research into three functional levels: sensorimotor behavior, reusable units, and task organization. This functional perspective brings together reinforcement learning approaches, vision-language-action models, world models, and code-as-policy methods. The taxonomy supports comparison within functional categories and the transfer of ideas across approaches, offering insights for future algorithm development toward more adaptable embodied systems.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 6472-6480
Interactive Interior Design Recommendation via Coarse-to-fine Multimodal Reinforcement Learning
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 6472-6480
Open AccessInteractive Interior Design Recommendation via Coarse-to-fine Multimodal Reinforcement Learning