Zifan Wang

KTH Royal Institute of Technology

Stockholm, Sweden

I am a fourth-year Ph.D. student affiliated with Division of Decision and Control Systems (DCS) at KTH Royal Institute of Technology. I am fortunate to jointly work with Prof. Karl H. Johansson at KTH and Prof. Michael M. Zavlanos at Duke University.

From January to April 2026, I was visiting Learning & Adaptive Systems Group at ETH Zurich, hosted by Prof. Andreas Krause. Prior to my PhD, I received both the master and bachelor degrees at Honors School of Harbin Institute of Technology.

I am broadly interested in the intersection of generative model, control, machine learning, and optimal transport. I have worked on research topics including distributionally robust optimization, CVaR optimization, distributional reinforcement learning in LQR, decision-dependent optimization. Lately, I have been exploring generative models with a special focus on flow matching models.

news

Jan 15, 2016	A simple inline announcement with Markdown emoji!
Nov 07, 2015	A long announcement with details
Oct 22, 2015	A simple inline announcement.

selected publications

ICML

Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning

Zifan Wang, Riccardo De Santi, Xiaoyu Mo, and 3 more authors

In International Conference on Machine Learning, 2026

arXiv
ICLR

Source-Guided Flow Matching

Zifan Wang, Alice Harting, Matthieu Barreau, and 2 more authors

In International Conference on Learning Representations, 2026

arXiv
NeurIPS

Outlier-robust distributionally robust optimization via unbalanced optimal transport

Zifan Wang, Yi Shen, Michael M Zavlanos, and 1 more author

In Advances in Neural Information Processing Systems, 2024
ICML

Risk-averse no-regret learning in online convex games

Zifan Wang, Yi Shen, and Michael Zavlanos

In International conference on machine learning, 2022
L4DC

Policy evaluation in distributional LQR

Zifan Wang, Yulong Gao, Siyi Wang, and 3 more authors

In Learning for dynamics and control conference, 2023
Automatica

Distributionally Robust Federated Learning with Outlier Resilience

Zifan Wang, Xinlei Yi, Xenia Konti, and 2 more authors

Automatica, 2026
IEEE TAC

Constrained optimization with decision-dependent distributions

Zifan Wang, Changxin Liu, Thomas Parisini, and 2 more authors

IEEE Transactions on Automatic Control, 2025
IEEE TAC

Policy Evaluation in Distributional LQR

Zifan Wang, Yulong Gao, Siyi Wang, and 3 more authors

IEEE Transactions on Automatic Control, 2025
IEEE TAC

Asymmetric learning in convex games

Zifan Wang, Xinlei Yi, Yi Shen, and 2 more authors

IEEE Transactions on Automatic Control, 2025
PhysRev

Can Quantum-Mechanical Description of Physical Reality Be Considered Complete?

A. Einstein^*†, B. Podolsky^*, and N. Rosen^*

Phys. Rev., New Jersey. More Information can be found here , May 1935

Abs DOI HTML PDF Video

In a complete theory there is an element corresponding to each element of reality. A sufficient condition for the reality of a physical quantity is the possibility of predicting it with certainty, without disturbing the system. In quantum mechanics in the case of two physical quantities described by non-commuting operators, the knowledge of one precludes the knowledge of the other. Then either (1) the description of reality given by the wave function in quantum mechanics is not complete or (2) these two quantities cannot have simultaneous reality. Consideration of the problem of making predictions concerning a system on the basis of measurements made on another system that had previously interacted with it leads to the result that if (1) is false then (2) is also false. One is thus led to conclude that the description of reality as given by a wave function is not complete.