CV

Education

B.S. in Applied Mathematics, University of Science and Technology of China (USTC), 2015-2019
M.S. in Electrical Engineering, Texas A&M University, 2019-2022
Ph.D in Computer Science, Texas A&M University, 2023-present

My research spans optimization theory, machine learning, and practical AI systems, with focus on fairness, efficiency, and multi-agent learning.

Fall 2025 – present: Multi-agent Joint Training in Large Language Models
Summer 2025 – present: Quantization in Large Language Models
Fall 2023 – present: Fairness in Submodular Optimization
Summer 2022 – Spring 2023: Uncertainty in Motion Planning for Autonomous Driving
Fall 2021 – Summer 2022: Goal-oriented Reinforcement Learning
Fall 2019 – Fall 2020: Partial Ranking Data Aggregation

Programming: Python, C/C++, MATLAB, Mathematica, LaTeX
Machine Learning: PyTorch, TensorFlow, Scikit-Learn, Transformers, Reinforcement Learning
Optimization: Linear/Integer Programming (CPLEX, CVXPY), Convex Optimization, Submodular Optimization, Bayesian Optimization
Data Tools: SQL, Pandas, NumPy, Dynamic Dashboards

Fall 2024: “Threshold Adaptive Sampling for Submodular Maximization under Bandit Feedback” (AI Seminar, Texas A&M University)

For a complete list of publications, please see my Google Scholar profile.

W. Chen, S. Xing, S. Zhou, V. Crawford. “Fair Submodular Cover.” ICLR 2025.
W. Chen, V. Crawford. “Linear Submodular Maximization with Bandit Feedback.” AISTATS 2025.
W. Chen, S. Xing, V. Crawford. “Adaptive Threshold Sampling for Pure Exploration in Submodular Bandits.” UAI 2025.

W. Chen, V. Crawford. “Bicriteria Approximation Algorithms for the Submodular Cover Problem.” NeurIPS 2023.

W. Chen, C. Tian. “A New Approach to Compute Information Theoretic Outer Bounds and Its Application to Regenerating Codes.” ISIT 2022.
W. Chen, R. Zhou, C. Tian, C. Shen. “On Top-k Selection from m-wise Partial Rankings via Borda Counting.” IEEE Transactions on Signal Processing, Vol. 70, pp. 2031–2045, 2022.
M. Yin*, W. Chen*, M. Wang, Y. Wang. “Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality.” UAI 2022. (*Equal contribution)