Xiangyang Xue

One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models

Self-learning Compositional Representations for Zero-shot Chinese Character Recognition

Compositional Scene Modeling with An Object-Centric Diffusion Transformer

Topo-Field: Topometric mapping with Brain-inspired Hierarchical Layout-Object-Position Fields

Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning

Federated Unlearning with Diffusion Models

Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection

MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing

Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs

Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection

Unsupervised Learning of Object-Centric Representation from Multi-Viewpoint Scenes