Generating text-rich images from prompts requires both textual fidelity and the coherent integration of text into the surrounding image. An explicit layout can provide structured guidance about what text should appear and where, but a well-formed plan alone does not guarantee that the renderer will realize it faithfull...
Guan-Qiao Chen, Jing Tan, Dong-Xing Mao et al.· 0 citations
Experiments show that BehR-based training improves long-term alignment in several settings, with the clearest gains in WebShop and less movement in near-ceiling regimes, while preserving or improving single-step prediction quality in three of four settings.
Youling Huang, Guan-Qiao Chen, Junchi Yao et al.· arXiv.org· 4 citations
SFAD is presented, a speculative decoding framework that enhances contextual faithfulness without inference degradation and substantially improves faithfulness while achieving $2.48\times$ speedup, offering a practical solution for efficient LLMs.
Guan-Qiao Chen, Di Wang, Lijie Hu· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.