BiDPO: Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
CVPR, 2026
Ph.D. Candidate
School of Computer Science,
Fudan University & Shanghai Innovation Institute
I am a fourth-year Ph.D. candidate at Fudan University and Shanghai Innovation Institute , supervised by Prof. Zuxuan Wu. Before that, I received my B.S. degree from Xi'an Jiaotong University in 2022. I am currently working as a research intern at Qwen , supervised by Shuai Bai and Lingchen Meng.
My research interests span large multimodal models and visual content generation, with a particular focus on fine-grained multimodal understanding and generation. I am expected to graduate in 2027 and am actively seeking job opportunities. Please feel free to reach out to me via email: wjpeng24[AT]m[DOT]fudan[DOT]edu[DOT]cn .
CVPR, 2026
NeurIPS, 2025
CVPR, 2024
TMM, 2024
TPAMI, 2024
Under review