Junlin Li

Publication

• UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement
• Improved Adversarial Diffusion Compression for Real-World Video Super-Resolution
• Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment
• OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation
• Q-Insight: Understanding Image Quality via Visual Reinforcement Learning
• ResVR: Joint Rescaling and Viewport Rendering of Omnidirectional Images