46 citations
- University of Hong KongHK7 papers
- Hong Kong Baptist UniversityHK6 papers
- Tsinghua UniversityCN4 papers
- Hong Kong University of Science and TechnologyHK3 papers
- Peng Cheng LaboratoryCN3 papers
- Shantou UniversityCN3 papers
- South China University of TechnologyCN3 papers
- Xiamen UniversityCN3 papers
- Chinese Academy of SciencesCN2 papers
- Nanyang Technological UniversitySG2 papers
- Southwest Jiaotong UniversityCN2 papers
- Sun Yat-sen UniversityCN2 papers
22 papers
Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout Generation
Zhijing Yang, Haocheng Lin, Zhihua Xu +4
Generating realistic interior furniture layouts that strictly adhere to architectural constraints (e.g., walls, doors, and windows) remains a fundamental challenge in automated spa…
Learnable Weighting of Intra-Attribute Distances for Categorical Data Clustering with Nominal and Ordinal Attributes
Yiqun Zhang, Yiu-ming Cheung
The success of categorical data clustering generally much relies on the distance metric that measures the dissimilarity degree between two objects. However, most of the existing cl…
Presence versus absence of charging energies in PbTe quantum dots
Yuhao Wang, Lining Yang, Wenyu Song +18
Charging energy () is essential in quantum dot (QD) devices. Previous studies on PbTe QDs have reported both the presence and absence of . To resolve this ambiguity, we v…
Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework
Yuchen He, Peizhi Ying, Liqi Cheng +4
Chart data extraction, which reverse-engineers data tables from chart images, is essential for reproducibility, analysis, retrieval, and redesign. Existing interactive tools are re…
Bridge the Gaps: Heterogeneous Attributed Graph Clustering via Quaternion Representation Learning
Xinxi Chen, Junyang Chen, Yiqun Zhang +2
Attributed graph clustering partitions nodes by jointly exploiting node attributes and graph topology. It remains challenging due to attribute heterogeneity and representation degr…
CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation
Kailun Huang, Zikang Xie, Yanzhe Xie +8
Humans primarily rely on walking and running to traverse complex terrains. Similarly, humanoid robots should be able to smoothly transition between walking and running while mainta…