Poster · Sydney
Read It Back: Pretrained MLLMs Are Zero-shot Reward Models for Text-to-Image Generation
- When
- Tue 8 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 1
- Authors
- Runhui Huang, Qihui Zhang, Zhe Liu, Yu Gao, Jie Wu, Hengshuang Zhao
- Organisations
- University of Hong Kong, Peking University, Huazhong University of Science and Technology, ByteDance
- QRS classification
- Generative models, Computer vision