← Search

Jiaxiu Jiang

2 accepted papers

2026

HP-Edit: A Human-Preference Post-Training Framework for Image Editing

CVPR 2026

Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (RL) methods such as Diffusion-DPO and Flow-GRPO have further improved generation quality, efficiently applying Reinforce

Cited by 0SourceScholar
2025

MC^2: Multi-concept Guidance for Customized Multi-concept Generation

CVPR 2025poster

Customized text-to-image generation, which synthesizes images based on user-specified concepts, has made significant progress in handling individual concepts. However, when extended to multiple concepts, existing methods often struggle with properly integrating different models and avoiding the unin…