Search papers, labs, and topics across Lattice.
ByteDance {zhs, ylliu, xbai}@hust.edu.cn, jingquntang@bytedance.com https://github.com/CIawevy/TextPecker
1
0
3
10
Even state-of-the-art text-to-image models like Qwen-Image can be significantly improved in structural fidelity and semantic alignment of rendered text using a novel RL strategy that rewards structural anomaly quantification.
