Chenxin Li

7 papers The Chinese University of Hong Kong

• DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
• FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning
• HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation
• IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering
• JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
• Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables
• Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables