Xun Wang

Xun Wang

I am a first-year Ph.D. student @ IIIS, Tsinghua.

About Me

Hi! I am Xun Wang (汪洵 in Chinese).

I am currently a first-year Ph.D. student at Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, where I am fortunate to be advised by Prof. Longbo Huang. Prior to this, I earned a Bachelor of Science degree in 2024 from the School of Computer Science at Nanjing University.

I am generally interested in AI for Decisions, especially for Reinforcement Learning (RL) algorithms and their applications.

News

  • Jul. 2025: Paper “Beyond Static Populations: Efficient Delay-Constrained Scheduling for Dynamic Users via Deep Reinforcement Learning” accepted to MobiHoc 2025!
  • Jul. 2025: Paper “Online Adaptable Offline RL with Guidance Model” accepted to TNNLS!
  • Mar. 2025: Paper “Mixed Sparsity Training: Achieving 4x FLOP Reduction for Transformer Pretraining” accepted to TMLR!
  • Dec. 2024: Paper “Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration” accepted to AAMAS 2025!
  • Jul. 2023: Paper “SDV: Simple Double Validation Model-based Offline Reinforcement Learning” accepted to ECAI 2023!

Publications

* indicates equal contribution

  • Xun Wang*, Zhuoran Li*, Longbo Huang, Beyond Static Populations: Efficient Delay-Constrained Scheduling for Dynamic Users via Deep Reinforcement Learning, the 26th International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc), Jul. 2025.

  • Xun Wang, Jingmian Wang, Zhuzhong Qian and Bolei Zhang. Online Adaptable Offline RL with Guidance Model, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), Jul. 2025. [Early Access]

  • Pihe Hu*, Shaolong Li*, Xun Wang, Longbo Huang, Mixed Sparsity Training: Achieving 4x FLOP Reduction for Transformer Pretraining, Transactions on Machine Learning Research (TMLR), Mar. 2025. [pdf] [code]

  • Hai Zhong, Xun Wang, Zhuoran Li, Longbo Huang, Offline-to-Online Multi-Agent Reinforcement Learning with Offline Value Function Memory and Sequential Exploration, the 24th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), May 2025. [arXiv]

  • Xun Wang, Haonan Chen, Junming Yang, Zhuzhong Qian and Bolei Zhang. SDV: Simple Double Validation Model-based Offline Reinforcement Learning, Proceedings of 26th European Conference on Artificial Intelligence (ECAI), Sept. 2023. Oral. [pdf] [code]