Hong Wang 王泓

I’m Wang Hong, a PhD student of MRIA Lab at the University of Science and Technology of China (USTC).
My recent research has primarily focused on: RLVR, RL agents, AI4PDE, AI for scientific computing.
I welcome discussions and collaborations with anyone interested in these fields. I have many ideas in the pipeline and am more than happy to share them.
I am currently on the job market — feel free to reach out if you are interested! 📄 [Download CV] 📊 [Research Slides].

Education

• B.S, Theoretical Physics
  School of Gifted Young, USTC, Anhui, China, 2017-2021
  
• B.S, Mathematics(double degree)
  School of Gifted Young, USTC, Anhui, China, 2017-2021
  
• M.S, Computational Mathematics
  School of Mathematical Sciences, USTC, Anhui, China, 2021-2023
  My supervisor: Prof.Kuan Xu
  
• Ph.D read, Electronic and Information Engineering
  School of Information Science and Technology, USTC, Anhui, China, 2023-2026
  My supervisor: Prof.Jie Wang
  

Internship Experience

• Internship at Tencent AI Code Assistant (CSIG CodeBuddy) Team (青云计划)
  Tencent CodeBuddy, Shenzhen, China, April 2025 - November 2025.
  Code LLM Reinforcement Learning

Awards

• Doctorate National Scholarship, the University of Science and Technology of China
  
• Outstanding Graduate, the University of Science and Technology of China
  
• ICLR 2024 financial assistance
  
• NeurIPS 2025 financial assistance
  

Contact me

• Email：wanghong1700@mail.ustc.edu.cn
• Wechat: wh1732060534
• QQ: 1732060534
• Phone: 17318588680

Selected Publications (Google Scholar)

Scientific computing (Published)

• Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
  Hong Wang*, Zhongkai Hao*, Jie Wang†, Zijie Geng, Zhen Wang, Bin Li, Feng Wu
  International Conference on Learning Representations (ICLR), Spotlight, 2024
  [arXiv]

• Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training
  Hong Wang*, Haiyang Xin*, Jie Wang†, Xuanze Yang, Fei Zha, Huanshuo Dong, Yan Jiang†
  Conference on Neural Information Processing Systems (NeurIPS), 2025
  [arXiv] [code]

• SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning
  Hong Wang, Jie Wang†, Minghao Ma, Haoran Shao, Haoyang Liu
  Conference on Neural Information Processing Systems (NeurIPS), 2025
  [arXiv] [code]

• STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem
  Hong Wang*, Jiang Yixuan*, Jie Wang†, Xinyi Li, Jian Luo, Huanshuo Dong
  Conference on Neural Information Processing Systems (NeurIPS), 2025
  [arXiv] [code]

• Self-Attention to Operator Learning-based 3D-IC Thermal Simulation
  Zhen Huang*, Hong Wang*, Wenkai Yang, Muxi Tang, Depeng Xie, TingJung Lin, Yu Zhang, Wei W. Xing†, Lei He†
  Design Automation Conference (DAC), 2025
  [arXiv]

• Accelerating PDE Data Generation via Differential Operator Action in Solution Space
  Huanshuo Dong, Hong Wang, Haoyang Liu, Jian Luo, Jie Wang†
  International Conference on Machine Learning (ICML), 2024
  [arXiv]

• Neural Krylov Iteration for Accelerating Linear System Solving
  Jian Luo, Jie Wang†, Hong Wang, Huanshuo Dong, Zijie Geng, Hanzhu Chen, Yufei Kuang
  Conference on Neural Information Processing Systems (NeurIPS), Spotlight, 2024
  [NeurIPS]

• Coordinate transform Fourier neural operators for symmetries in physical modelings
  Wenhan Gao, Ruichen Xu, Hong Wang, Yi Liu†
  Transactions on Machine Learning Research (TMLR), 2024
  [OpenReview]

Large Language Model (Published)

• Exploiting Edited Large Language Models as General Scientific Optimizers
  Qitan Lv*, Tianyu Liu*, Hong Wang†
  North American Chapter of the Association for Computational Linguistics (NAACL), 2025
  [arXiv]

• Perturbation-Restrained Sequential Model Editing
  JunYu Ma, Hong Wang, HaoXiang Xu, Zhen-Hua Ling, JiaChen Gu†
  International Conference on Learning Representations (ICLR), 2025
  [arXiv]

Selected Under Submission

• Scheduling Your LLM Reinforcement Learning with Reasoning Trees
  Hong Wang*, Zhezheng Hao*, Jian Luo, Chenxing Wei, Yao Shu, Lei Liu, Qiang Lin, Hande Dong†, Jiawei Chen†
  Submitted to International Conference on Learning Representations (ICLR), 2026
  [arXiv] [code]

• Accelerating Eigenvalue Dataset Generation via Chebyshev Subspace Filter
  Hong Wang, Jie Wang†, Jian Luo, Huanshuo Dong, Yeqiu Chen, Runmin Jiang, Zhen Huang
  Submitted to International Conference on Learning Representations (ICLR), 2026
  [arXiv]

• Accelerating IC Thermal Simulation Data Generation via Block Krylov and Operator Action
  Hong Wang, Wenkai Yang, Jie Wang, Huanshuo Dong, Zijie Geng, Zhen Huang, Depeng Xie, Zhezheng Hao, Hande Dong
  Submitted to Design Automation Conference (DAC), 2026
  [arXiv]

• Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective
  Zhezheng Hao*, Hong Wang*, Haoyang Liu, Jian Luo, Jiarui Yu, Hande Dong†, Qiang Lin, Can Wang, Jiawei Chen†
  Submitted to International Conference on Learning Representations (ICLR), 2026
  [arXiv] [code]

• Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs
  Chenxing Wei, Hong Wang, Ying He, Fei Yu, Yao Shu†
  Submitted to International Conference on Learning Representations (ICLR), 2026
  [arXiv]

• Accelerating Data Generation for Nonlinear temporal PDEs via Homologous Perturbation in Solution Space
  Lei Liu*, Zhenxin Huang*, Hong Wang†, Huanshuo Dong, Haiyang Xin, Hongwei Zhao, Bin Li
  Submitted to International Conference on Learning Representations (ICLR), 2026
  [arXiv]

• From Uniform to Adaptive: General Skip-Block Mechanisms for Efficient PDE Neural Operators
  Lei Liu*, Zhongyi Yu*, Hong Wang†, Huanshuo Dong, Haiyang Xin, Hongwei Zhao, Bin Li
  Submitted to International Conference on Learning Representations (ICLR), 2026
  [OpenReview]

• GAPO: Group Adaptive Policy Optimization for Real-World Code Edit
  Jianqing Zhang, Zhezheng Hao, Wei Xia†, Hande Dong, Hong Wang, Chenxing Wei, Yuyan Zhou, Yubin Qi, Qiang Lin, Jian Cao†
  [arXiv] [code]