arXiv:2609.38920v1 Announce Type: new
Abstract: Offline multi-objective optimization (MOO) seeks solutions with better objective trade-offs using only a fixed dataset, without querying the objectives...
By Yuan Lu, Esha Singh, Yi-An Ma, Yusu Wang
Offline multi-objective optimization (MOO) seeks solutions with better objective trade-offs using only a fixed dataset, without querying the objectives. Diffusion models trained on such data have emer...
arXiv:2606. 15115v1 Announce Type: new Abstract: Multi-objective optimization (MOO) has emerged as a powerful approach to solving complex optimization problems involving multiple objectives.
By Yiyi Zhu, Yaolin Wen, Xiang Xia, Xin An, Hanyi Si, Xiang Shu, Yangde Fu, Liang Dou, Hong Qian
ParetoTransport is a training‑free guidance method for pre‑trained flow‑matching models that explicitly refines a population‑level distribution in objective space. It iteratively transports the empirical offline distribution toward the Pareto front using Wasserstein matching to intermediate proxy distributions, thereby controlling distributional displacement and mass allocation along the front. The authors prove a convergence result and show state‑of‑the‑art performance on standard offline multi‑objective optimization benchmarks, evaluating beyond hypervolume to generational distance, inverted generational distance, and Wasserstein distance.
By Stephanie Holly, Sepp Hochreiter, Werner Zellinger
arXiv:2602. 03901v5 Announce Type: replace Abstract: The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization.
By Rong Fu, Chunlei Meng, Haoyu Zhao, Kun Liu, JiaBao Dou, Youjin Wang, Simon James Fong
COFFEE is a plug‑and‑play framework that enables future‑aware guidance for discrete diffusion models by separating sequence dependence from the objective. It uses a target‑free carrier to absorb marginal token distributions and a compiled finite‑state model to capture how token combinations affect sequence‑level preferences, allowing global preferences to be transferred to unresolved positions without retraining the diffusion model. The framework supports both hard constraints and learned soft objectives and demonstrates strong control results across symbolic, language, and biological benchmarks.
By Hua (Edward), Xu, Dongxin Li, Gwen Yidou-Weng, Guy Van den Broeck, Wei Wang, Anji Liu