Search papers, labs, and topics across Lattice.
Westlake University, Zhejiang University, Shanghai Innovation Institute
2
0
4
Current image generation models struggle with rendering dense, multi-region text, with fidelity dropping by over 14 points when clarity is prioritized.
High-fidelity image synthesis does not require paired text from day one: pre-training visual priors on uncaptioned images before multimodal alignment beats conventional joint training pipelines to establish a new open-source DiT benchmark.
