Chao Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chao Wang has a total of 129 co-authors. Here are the top co-authors by number of shared publications:
- Yan Peng
Shanghai University
13 shared publications Yang Zhou
8 shared publications- Yang Zhou
School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
7 shared publications - Jingping Liu
School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China
5 shared publications Yan Peng
5 shared publications- Yanghua Xiao
Fudan University
5 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8135-8143
CoRe-RAG: Trustworthy Multimodal Retrieval via Adaptive Conformal Prediction and Logical-Utility Alignment
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8135-8143
Open AccessCoRe-RAG: Trustworthy Multimodal Retrieval via Adaptive Conformal Prediction and Logical-Utility Alignment
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16065-16074
Loci-GS: Full-Automatic Disentangled 3D Asset Placement in 3D Gaussian Scene via Language Grounding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16065-16074
Open AccessLoci-GS: Full-Automatic Disentangled 3D Asset Placement in 3D Gaussian Scene via Language Grounding
- 14 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 346
A category-theoretic approach to causal equivalence: Mapping directed acyclic graphs to undirected prime graphs
- 14 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 346
A category-theoretic approach to causal equivalence: Mapping directed acyclic graphs to undirected prime graphs
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP (2162237X) , 1-15
Graph Rotation Network: Equivariant Graph Neural Network for Efficient Inverse Design in 4-D Printing
Four-dimensional printed structures transform shape under external stimuli, and designing these structures to achieve desired deformation outcomes is crucial for 4-D printing technology. Current machine-learning (ML)-assisted methods can design 4-D-printed structures rapidly and accurately, but often overlook the E(3) equivariance required for the model, leading to inconsistent prediction structure between different coordinate representations of the same structure. Consequently, many ML-assisted design approaches rely on data augmentation techniques such as rotation to improve the model’s generalization across different coordinate representations, but the method through data augmentation is inefficient. We observe that equivariant graph neural networks (GNNs), due to their equivariant properties, can address the inefficiencies associated with the aforementioned training augmentation. Therefore, we propose utilizing an equivariant GNN to improve these efficiencies. Nonetheless, existing equivariant GNNs struggle to balance computational efficiency with expressive power, which will impact their effectiveness in 4-D printing structure design. In response, we introduce a novel equivariant GNN, the graph rotation network (GRN), which approximates arbitrary E(3) equivariant functions by constructing a 3-D equivariant basis through rotations. This approach enhances the model’s performance with trainable rotational angles. We theoretically analyze the E(3) equivariance of our model as well as its computational complexity and empirically demonstrate the improved training efficiency introduced by equivariance. Finally, we apply GRN to both forward prediction and inverse design of 4-D-printed meshes. Our equivariant GNN significantly outperforms nonequivariant GNNs and other equivariant GNNs in forward prediction tasks. For inverse design, our method achieves an accuracy of 98.8% (relative to the mesh size), providing an effective tool for the design of 4-D-printed structures.
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP (2162237X) , 1-15
Graph Rotation Network: Equivariant Graph Neural Network for Efficient Inverse Design in 4-D Printing
Four-dimensional printed structures transform shape under external stimuli, and designing these structures to achieve desired deformation outcomes is crucial for 4-D printing technology. Current machine-learning (ML)-assisted methods can design 4-D-printed structures rapidly and accurately, but often overlook the E(3) equivariance required for the model, leading to inconsistent prediction structure between different coordinate representations of the same structure. Consequently, many ML-assisted design approaches rely on data augmentation techniques such as rotation to improve the model’s generalization across different coordinate representations, but the method through data augmentation is inefficient. We observe that equivariant graph neural networks (GNNs), due to their equivariant properties, can address the inefficiencies associated with the aforementioned training augmentation. Therefore, we propose utilizing an equivariant GNN to improve these efficiencies. Nonetheless, existing equivariant GNNs struggle to balance computational efficiency with expressive power, which will impact their effectiveness in 4-D printing structure design. In response, we introduce a novel equivariant GNN, the graph rotation network (GRN), which approximates arbitrary E(3) equivariant functions by constructing a 3-D equivariant basis through rotations. This approach enhances the model’s performance with trainable rotational angles. We theoretically analyze the E(3) equivariance of our model as well as its computational complexity and empirically demonstrate the improved training efficiency introduced by equivariance. Finally, we apply GRN to both forward prediction and inverse design of 4-D-printed meshes. Our equivariant GNN significantly outperforms nonequivariant GNNs and other equivariant GNNs in forward prediction tasks. For inverse design, our method achieves an accuracy of 98.8% (relative to the mesh size), providing an effective tool for the design of 4-D-printed structures.
- 7 March 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 340
Heuristically motivating large language models for task planning
- 7 March 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 340
Heuristically motivating large language models for task planning
- Top Cited Papers
- 6 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 178
LayoutDreamer: Physics-guided layout for text-to-3D compositional scene generation
- 6 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 178
Top Cited PapersLayoutDreamer: Physics-guided layout for text-to-3D compositional scene generation
- Open Access
- 4 March 2026
- Published by Elsevier in SSRN Electronic Journal
Multi-Material 4D Printed Smart Shape-Morphing Structures: Precise Finite Element Analysis
Multi-material 4D printing technology has garnered significant attention for its ability to create smart structures with complex, programmable shape-morphing capabilities. However, a persistent challenge in this field is the precise prediction of deformation in these smart structures, as existing research methods lack high-fidelity predictive models that bridge the gap between simulation and experiment. To overcome this obstacle, this study conducts precise material characterization experiments and high-fidelity finite element analysis (FEA) to reliably predict thermally induced shape transformations. Using a bilayer polylactic acid (PLA)/carbon fiber-reinforced polylactic acid (CFPLA) sheet as a case study, a numerical simulation model was developed in COMSOL Multiphysics that comprehensively considers thermo-mechanical coupling, viscoelasticity, and anisotropy, while also quantitatively accounting for the impact of printing process-induced residual stresses on the model's predictive accuracy. Subsequently, we designed various programmable material distribution patterns to simulate a diversity of structural thermal deformations driven by strain mismatch. To validate the fidelity of the aforementioned simulation prediction model, we fabricated and tested the thermal deformation of physical structures. The experimental results showed a high degree of consistency with the simulation results, achieving an average similarity of 95.5% ± 0.65% and a mean distance deviation of 1.65 ± 0.30 mm. This method provides a reproducible and practical tool for the forward design of 4D-printed smart structures.
- 4 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMulti-Material 4D Printed Smart Shape-Morphing Structures: Precise Finite Element Analysis
Multi-material 4D printing technology has garnered significant attention for its ability to create smart structures with complex, programmable shape-morphing capabilities. However, a persistent challenge in this field is the precise prediction of deformation in these smart structures, as existing research methods lack high-fidelity predictive models that bridge the gap between simulation and experiment. To overcome this obstacle, this study conducts precise material characterization experiments and high-fidelity finite element analysis (FEA) to reliably predict thermally induced shape transformations. Using a bilayer polylactic acid (PLA)/carbon fiber-reinforced polylactic acid (CFPLA) sheet as a case study, a numerical simulation model was developed in COMSOL Multiphysics that comprehensively considers thermo-mechanical coupling, viscoelasticity, and anisotropy, while also quantitatively accounting for the impact of printing process-induced residual stresses on the model's predictive accuracy. Subsequently, we designed various programmable material distribution patterns to simulate a diversity of structural thermal deformations driven by strain mismatch. To validate the fidelity of the aforementioned simulation prediction model, we fabricated and tested the thermal deformation of physical structures. The experimental results showed a high degree of consistency with the simulation results, achieving an average similarity of 95.5% ± 0.65% and a mean distance deviation of 1.65 ± 0.30 mm. This method provides a reproducible and practical tool for the forward design of 4D-printed smart structures.
- 25 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 339
Negative-Sampling prompt learning for hard negative sample discrimination
- 25 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 339
Negative-Sampling prompt learning for hard negative sample discrimination
- 28 January 2026
- Published by Elsevier in Information Sciences
- Vol. 739
Focal equilibrium: Bias reshaping for generalizable and robust visual understanding
- 28 January 2026
- Published by Elsevier in Information Sciences
- Vol. 739
Focal equilibrium: Bias reshaping for generalizable and robust visual understanding