Grab a Coffee: Future-Aware Guidance for Discrete Diffusion with Compiled Objectives
By making objectives available to inference rather than only evaluation, COFFEE brings joint conditioning, completion-weighted guidance, and optimization-based constraints into pretrained neural generation, showing the potential of neural-symbolic methods in diffusion guidance.
Hua-Qiu Xu, Dong-Xin Li, Gwen Yidou-Weng et al.
· 0 citations