Xiaowei Hu

Fine-Grained Prompt-Driven Stylization with Context-Aware Reasoning for Zero-Shot Domain Adaptation

DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis

Real-World Adverse Weather Image Restoration via Dual-Level Reinforcement Learning with High-Quality Cold Start

SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency

MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models

GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI