Xin Jin

6 papers Eastern Institute of Technology, Ningbo

• Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
• EDBench: Large-Scale Electron Density Data for Molecular Modeling
• SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
• UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes
• VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations