This work proposes Diffusion Online-guidance Fine-tuning (DOHF), which turns Doob's $h-transform into a practical online training algorithm and demonstrates how adapting probabilistic conditioning through inexpensive estimation and iterative distillation can improve generative learning across statistical sampling and v...
Zheng-Yi Guo, Jia-Yuan Sheng, Wen-Pin Tang et al.· 1 citation
A continuous-time RL framework for fine-tuning score-based discrete diffusion models, which enables reward-driven optimization without requiring differentiability on the reward signals, is developed.
Zikun Zhang, Jia-Yuan Sheng, David D. Yao et al.· arXiv.org· 1 citation
Spec2Twin-Chain is considered, a framework that formulates blockchain digital-twin construction as a bi-level optimization problem and can construct behaviorally accurate twins, improve initial designs through iterative feedback, and reuse calibrated twins to support downstream decisions.
Hao-Ting Zhang, Haoxian Chen, Jiayuan Sheng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.