Jingxing Wang

alt text 

Ph.D. Student
University of Washington

Email: jxwang1@uw.edu
Google Scholar | CV

About me

My research interests span machine learning, optimization, information theory and data-driven decision making.

I'm a second-year Ph.D. student at UW ECE, co-advised by Vasileios Charisopoulos and Maryam Fazel. Previously, I completed my undergraduate at UC Berkeley, where I worked with Kannan Ramchandran and his group at BLISS. I also collaborated with Chiwei Yan from the department of IEOR.

Publications

Stock diffusion transformer output compared with seamless tiles generated using Torus RoPE

Torus RoPE: Bridging Seamless Tile Generation to Diffusion Transformers Runjia Li, Ally Du, Jingxing Wang, Vasileios Charisopoulos, Maryam Fazel, Simon Du In submission

We built a training free method that lets diffusion transformers generate seamless tiles.

Convergence of gradient methods for overparameterized Gaussian mixtures

Local linear convergence of gradient methods for overparameterized Gaussian mixtures Jingxing Wang, Vasileios Charisopoulos, Maryam Fazel NeurIPS 2026

We show slowdown due to overparameterization can be reconciled by exploiting geometry.

Talk presented at the IFDS Weekly Seminar, University of Washington (Nov. 6, 2026).
Poster presented at the IFDS Research Expo and UW–Amazon Science Hub Robotics Showcase (2026).

Airline fleet assignment and scheduling network

A dynamic model for airline fleeting and scheduling Chiwei Yan, Jingxing Wang, Archis Ghate Operations Research

We built a model for airline scheduling that accounts for decision-dependent, stochastic demand,
and demonstrated its effectiveness using data from a major U.S. airline’s network of 997 flights.

Talk presented at the 2025 INFORMS Annual Meeting.

Awards and Honors

Rushmer Electrical Engineering Endowment Fellowship, 2025