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.

My research centers on optimization over probability distributions, at the intersection of control, optimization, and generative modeling. I am broadly interested in the intersection of generative model, control, and optimization. This perspective has carried me from control and optimal transport through robust, risk-sensitive learning, and now to steering generative models. My goal is to develop the mathematical and algorithmic foundations for reliable and controllable generative-model steering, and to translate these advances into applications such as scientific discovery.

Methods in Decision-Making

I develop distributional learning and optimization methods for decision-making and generative models.

Risk-Averse Learning

Distributionally Robust Optimization

Distributional RL

Decision-Dependent Optimization

Game-Theoretic Learning

Methods in Generative Modeling

I develop methods for adapting and steering generative models.

Applications

I have been focusing on developing general-purpose methods that transfer across domains. Examples:

Scientific Discovery

Tail-Aware Flow Fine-Tuning

Image Generation

Robotics & Transportation

SparScene

news

May 04, 2026	Travel grant from Signeuls Foundation
Apr 22, 2026	Two papers accepted at IFAC WC 2026!
Apr 15, 2026	One paper on Tail-aware Flow Fine-Tuning (TFFT) accepted at ICML 2026! TFFT is a risk-sensitive generative optimization method that allows to efficiently seek novel samples (in molecular design) and control worst cases (in text-to-image generation)!
Feb 24, 2026	One paper on Source-Guided Flow Matching (SGFM) accepted at ICLR 2026! SGFM is a new flow guidance method that modifies the source distribution!
Jun 13, 2025	I give a talk at ECC workshop in Thessaloniki, Greece

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 Bib Code

@inproceedings{wang2026efficient,
  title = {Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning},
  author = {Wang, Zifan and De Santi, Riccardo and Mo, Xiaoyu and Zavlanos, Michael M and Krause, Andreas and Johansson, Karl H},
  booktitle = {International Conference on Machine Learning},
  year = {2026},
}

ICLR

Source-Guided Flow Matching

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

In International Conference on Learning Representations, 2026

arXiv Bib

@inproceedings{wang2026sourceguided,
  title = {Source-Guided Flow Matching},
  author = {Wang, Zifan and Harting, Alice and Barreau, Matthieu and Zavlanos, Michael M and Johansson, Karl H},
  booktitle = {International Conference on Learning Representations},
  year = {2026},
}

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

Bib

@inproceedings{wang2024outlier,
  title = {Outlier-robust distributionally robust optimization via unbalanced optimal transport},
  author = {Wang, Zifan and Shen, Yi and Zavlanos, Michael M and Johansson, Karl H},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {37},
  pages = {52189--52214},
  year = {2024},
}

L4DC

Policy evaluation in distributional LQR

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

In Learning for dynamics and control conference, 2023

arXiv Bib

@inproceedings{wang2023policy,
  title = {Policy evaluation in distributional LQR},
  author = {Wang, Zifan and Gao, Yulong and Wang, Siyi and Zavlanos, Michael M and Abate, Alessandro and Johansson, Karl Henrik},
  booktitle = {Learning for dynamics and control conference},
  pages = {1245--1256},
  year = {2023},
  organization = {PMLR},
}

IEEE TAC

Constrained optimization with decision-dependent distributions

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

IEEE Transactions on Automatic Control, 2025

arXiv Bib

@article{wang2025constrained,
  title = {Constrained optimization with decision-dependent distributions},
  author = {Wang, Zifan and Liu, Changxin and Parisini, Thomas and Zavlanos, Michael M and Johansson, Karl H},
  journal = {IEEE Transactions on Automatic Control},
  year = {2025},
  publisher = {IEEE},
}

Automatica

Distributionally Robust Federated Learning with Outlier Resilience

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

Automatica, 2026

arXiv Bib

@article{wang2025distributionally,
  title = {Distributionally Robust Federated Learning with Outlier Resilience},
  author = {Wang, Zifan and Yi, Xinlei and Konti, Xenia and Zavlanos, Michael M and Johansson, Karl H},
  journal = {Automatica},
  year = {2026},
}

IEEE TAC

Asymmetric learning in convex games

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

IEEE Transactions on Automatic Control, 2025

arXiv Bib

@article{wang2025asymmetric,
  title = {Asymmetric learning in convex games},
  author = {Wang, Zifan and Yi, Xinlei and Shen, Yi and Zavlanos, Michael M and Johansson, Karl H},
  journal = {IEEE Transactions on Automatic Control},
  year = {2025},
  publisher = {IEEE},
}

IEEE TAC

Policy Evaluation in Distributional LQR

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

IEEE Transactions on Automatic Control, 2025

arXiv Bib

@article{wang2025policy,
  title = {Policy Evaluation in Distributional LQR},
  author = {Wang, Zifan and Gao, Yulong and Wang, Siyi and Zavlanos, Michael M and Abate, Alessandro and Johansson, Karl H},
  journal = {IEEE Transactions on Automatic Control},
  year = {2025},
  publisher = {IEEE},
}

ICML

Risk-averse no-regret learning in online convex games

Zifan Wang, Yi Shen, and Michael Zavlanos

In International conference on machine learning, 2022

arXiv Bib

@inproceedings{wang2022risk,
  title = {Risk-averse no-regret learning in online convex games},
  author = {Wang, Zifan and Shen, Yi and Zavlanos, Michael},
  booktitle = {International conference on machine learning},
  pages = {22999--23017},
  year = {2022},
  organization = {PMLR},
}

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.

Methods in Decision-Making

Risk-Averse Learning

Distributionally Robust Optimization

Distributional RL

Decision-Dependent Optimization

Game-Theoretic Learning

Methods in Generative Modeling

Risk-Sensitive Fine-Tuning

Inference-Time Guidance

Federated Generative Models

Applications

Scientific Discovery

Image Generation

Robotics & Transportation

news

selected publications