Zuxuan Wu

5 papers Fudan University

• ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
• INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
• OmniGen-AR: AutoRegressive Any-to-Image Generation
• Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control
• UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation