11 papers
Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning
Zifan Wang, Riccardo De Santi, Xiaoyu Mo +3
Fine-tuning pre-trained diffusion and flow models to optimize downstream utilities is central to real-world deployment. Existing entropy-regularized methods primarily maximize expe…
SparScene: Efficient Traffic Scene Representation via Sparse Graph Learning for Large-Scale Trajectory Generation
Xiaoyu Mo, Jintian Ge, Zifan Wang +2
Multi-agent trajectory generation is a core problem for autonomous driving and intelligent transportation systems. However, efficiently modeling the dynamic interactions between nu…
Wasserstein Distributionally Robust Nash Equilibrium Seeking with Heterogeneous Data: A Lagrangian Approach
Zifan Wang, Georgios Pantazis, Sergio Grammatico +2
We study a class of distributionally robust games where agents are allowed to heterogeneously choose their risk aversion with respect to distributional shifts of the uncertainty. I…
Distributionally Robust Federated Learning with Outlier Resilience
Zifan Wang, Xinlei Yi, Xenia Konti +2
Federated learning (FL) enables collaborative model training without direct data sharing, but its performance can degrade significantly in the presence of data distribution perturb…
Federated Flow Matching
Zifan Wang, Anqi Dong, Mahmoud Selim +2
Data today is decentralized, generated and stored across devices and institutions where privacy, ownership, and regulation prevent centralization. This motivates the need to train…
Asymmetric Feedback Learning in Online Convex Games
Zifan Wang, Xinlei Yi, Yi Shen +2
This paper considers convex games involving multiple agents that aim to minimize their own cost functions using locally available information. A common assumption in the study of s…