👨🏻💻 About Me
I am currently a second-year master student with the School of Computer Science, Shanghai Jiao Tong University (上海交通大学计算机学院). I have been a member of ReThinkLab since 2022 and supervised by Prof. Junchi Yan (严骏驰) who leads the lab. I obtained my Bachelor of Engineering Degree from the Department of Computer Science and Engineering (IEEE Honors Class, subject to a provincial top 0.01% ranking in the College Entrance Exam) of SJTU in 2024. Recently, I have been admitted to Shanghai Innovation Institute (上海创智学院), where I’m planning to start my Ph.D. program in 2027.
My research interests include learning to solve complex discrete optimization problems (neural combinatorial optimization in particular), generative models, machine learning on graphs, and broader fields towards large decision-making models and scientific intelligence. More recently, I’ve also started to explore the intersection of large language models (LLMs) as well as agentic systems with my major research directions.
📖 Educations
📝 Selected Publications
(CCF-A) Problem Distributions as Tasks: Repurposing Meta Learning for Generative Combinatorial Optimization towards Multi-task Pretraining and Adaptation [PDF][Code 
Wenzheng Pan, Jiale Ma, Nuoyan Chen, Yang Li, Junchi Yan
We introduce M²GenCO, a meta-generative framework that treats problem distributions as tasks to enable efficient multi-task pretraining, few-shot adaptation, and robust generalization across graph-based combinatorial optimization problems.
(CCF-A) Design Linear Constrained Neural Layers with Implicit Convex Optimization [PDF]
Junchi Yan, Jiaxi Liu, Yihui Tu, Fangyuan Zhou, Wenzheng Pan, Zhongteng Gui, Liangliang Shi
We propose LinConLayer, a plug-in differentiable neural layer that enforces general linear constraints via implicit convex optimization, yielding efficient BLCLayer and GLCLayer variants for constrained prediction in tasks such as graph matching, portfolio allocation, and linear programming.
(CCF-A) ML4CO-Bench-101: Benchmark Machine Learning
for Classic Combinatorial Problems on Graphs [PDF][Code 
Jiale Ma, Wenzheng Pan, Yang Li, Junchi Yan
We establishe ML4CO-Bench-101, a standardized benchmark and modular evaluation framework that systematically categorizes, reproduces, and compares neural solvers across seven mainstream graph-based combinatorial optimization problems.
(CCF-A) COExpander: Adaptive Solution Expansion for Combinatorial Optimization [PDF][Code 
Jiale Ma*, Wenzheng Pan*, Yang Li, Junchi Yan
We introduce COExpander, an adaptive expansion paradigm that bridges global prediction and local construction by progressively determining decision variables with dynamically controlled step sizes for scalable combinatorial optimization.
(CCF-A) UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP [PDF] [Code 
Wenzheng Pan*, Hao Xiong*, Jiale Ma, Wentao Zhao, Yang Li, Junchi Yan
We propose UniCO, a unified neural combinatorial optimization framework that reduces diverse COPs into matrix-encoded general TSP and solves them with tailored matrix-based RL and diffusion solvers: 1) MatPOENet, an RL-based sequential model with pseudo one-hot embedding (POE) scheme and 2) MatDIFFNet, a Diffusion-based generative model with the mix-noised reference mapping scheme.
(CCF-A) Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search [PDF][Code 
Yang Li, Jiale Ma, Wenzheng Pan, Runzhong Wang, Haoyu Geng, Nianzu Yang, Junchi Yan
We present ML4TSPBench, a modular framework that decomposes learning-based TSP solvers into reusable learning and search components, revealing key design principles for stronger and more principled ML4CO methods.
(CCF-A) Pygmtools: A Python Graph Matching Toolkit [PDF][Code 
Runzhong Wang, Ziao Guo, Wenzheng Pan, Jiale Ma, Yikai Zhang, Nan Yang, Qi Liu, Longxuan Wei, Hanxue Zhang, Chang Liu, Zetian Jiang, Xiaokang Yang, Junchi Yan
We release Pygmtools, an open-source Python toolkit that unifies classical, multi-graph, and learning-based graph matching solvers across multiple numerical backends for research and practical applications.
⚙️ Open Source Projects
A curated collection of literature in the ML4CO field, organized to support researchers in accessing both foundational and recent developments. This repository is maintained with a joint effort by members in SJTU-Thinklab as well as contributors from the community.
A general-purpose toolkit that provides implementations of common algorithms used in ML4CO, along with basic training frameworks, traditional solvers and data generation tools. It aims to simplify the implementation of key techniques and offer a solid base for developing machine learning models for COPs.
A benchmark focusing on exploring the TSP for representativeness. It offers a deep dive into various methodology designs, enabling comparisons and the development of specialized algorithms.
A benchmark that categorizes neural combinatorial optimization (NCO) solvers by solving paradigms, model designs, and learning strategies. It evaluates applicability and generalization of different NCO approaches across a broad range of combinatorial optimization problems to uncover universal insights that can be transferred across various domains of ML4CO.
A Python graph matching toolkit that implements a comprehensive collection of two-graph matching and multi-graph matching solvers, covering both learning-free solvers as well as learning-based neural graph matching solvers. Our implementation supports numerical backends including Numpy, PyTorch, Jittor, Paddle, runs on Windows, MacOS and Linux, and is friendly to install and configure.
🎖 Honors and Awards
🔍 Academic Services
- Reviewer: ICML’26 (Gold Reviewer), NeurIPS’25-26, ICLR’25-27, AAAI’27, AAMAS’26.