Xipeng Qiu
- ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
- INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
- Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
- Pre-Trained Policy Discriminators are General Reward Models
- World-aware Planning Narratives Enhance Large Vision-Language Model Planner