Welcome to my homepage!

Beginning in August 2026, I will be a Postdoctoral Research Fellow at Johns Hopkins University, working with Prof. Fei Lu and Prof. Mauro Maggioni.

I received my Ph.D. in Statistics from the University of Wisconsin-Madison, where I was very fortunate to be advised by Prof. Nicolás García Trillos and Prof. Qin Li. Before UW-Madison, I earned my B.S. in Mathematics and Statistics from Nanjing University in Nanjing, China.

My current research lies in the intersection of applied mathematics and machine learning, with a particular focus on Interacting Particle Systems, Theoretical Foundation of Transformers, Multi-Agent-Based Learning, and Generative Modeling.

My full CV can be found here.

Email: sli739@wisc.edu

Publications

Interacting Particle Systems for ML

• Defending Against Diverse Attacks in Federated Learning Through Consensus-Based Bi-Level Optimization
  Nicolás García Trillos, Aditya Kumar Akash, Sixu Li*, Konstantin Riedl, Yuhua Zhu
  Philosophical Transactions A, 2025

• FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization
  José A. Carrillo, Nicolás García Trillos, Sixu Li*, Yuhua Zhu
  Journal of Machine Learning Research, 2024

• CB²O: Consensus-Based Bi-Level Optimization
  Nicolás García Trillos, Sixu Li*, Konstantin Riedl, Yuhua Zhu
  Under Review

• Optimal Drift Optimizer for Non-convex Optimization
  Qin Li, Sixu Li*, Eitan Tadmor, Emmanuel Trélat
  Under Review

• On the Diverse Dynamical Behavior of Deep Linear Transformers
  Sixu Li, Thomas Jake Maranzatto, Jan Peszek, Trevor Teolis, Semih Akkoc, Konstantin Riedl Sennur Ulukus, Nicolás García Trillos
  Preprint

Generative Modeling

• When Does Noise Help in Stochastic Interpolants: A Non-Asymptotic Analysis and Optimal Design
  Sixu Li, Ethan Hanold, Nicholas Boffi, Leonardo Zepeda-Núñez, Qin Li
  In preparation

• A Good Score Does not Lead to A Good Generative Model
  Sixu Li, Shi Chen, Qin Li
  Preprint

Others

• Wasserstein Barycenter-based Model Fusion and Linear Mode Connectivity of Neural Networks
  Aditya Kumar Akash, Sixu Li, Nicolás García Trillos
  Preprint

(* indicates alphabetic authorship)

Teaching Experiences

• Fall 2025:
  STAT 303: R for Statistics I & STAT 628: Data Science Practicum (TA)
• Spring 2025:
  STAT 333: Applied Linear Regression (TA)
• Fall 2024:
  STAT 628: Data Science Practicum (TA)
• Spring 2024, 2023, 2022:
  STAT 615: Statistical Learning (TA)
• Fall 2023:
  STAT 605: Data Science Computing Project (TA)
• Summer 2023, Fall 2022:
  STAT 301: Introduction to Statistical Methods (TA)
• Fall 2021:
  STAT 312: Introduction to Theory and Methods of Mathematical Statistics II (TA)