I am currently an Associate Professor in the School of Cyber Science and Technology at Sun Yat-sen University. My research is driven by a fundamental question: How can intelligent agents learn, adapt, and make decisions in complex and evolving environments? My current interests span reinforcement learning, continual learning, LLM optimization, LLM agents, and embodied AI.
Prior to joining Sun Yat-sen University, I was a postdoctoral researcher in the Department of Computer Science and Technology at Tsinghua University from 2023 to 2024. I received my Ph.D. from the School of Computer Science and Engineering at Central South University, where I was fortunate to be advised by Prof. Ju Ren.
During my Ph.D., I was also a visiting student at the Davis AI, Robotics, and Edge Lab from 2020 to 2022, where I was fortunate to work under the supervision of Prof. Junshan Zhang, and at the Decision Intelligence Lab in fall 2018, where I was fortunate to be advised by Prof. Longbo Huang.
Prospective students: If our research sounds interesting to you, feel free to get in touch!
Recent News
- Sep 2026
- I will serve as an AC at ICLR 2027.
- May 2026
- AdamO: A Collapse-Suppressed Optimizer for Offline RL is accepted to ICML 2026. We develop a new optimizer for more stable critic learning in offline RL. Congratulations to Nan!
- May 2026
- Executable Agentic Memory for GUI Agent is accepted to ICML 2026. We propose a new memory mechanism that enables GUI agents to effectively reuse historical execution trajectories. Congratulations to Zerui!
- May 2026
- Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization is accepted to ICML 2026. We introduce a new post-training approach based on a Bayesian reward that equips agentic LLMs with clever exploration capabilities. Congratulations to Xingyuan!
- Jan 2026
- Less Is More: Clustered Cross-Covariance Control for Offline RL is accepted to ICLR 2026. Congratulations to Nan!
- Jan 2026
- Context Learning for Multi-Agent Discussion is accepted to ICLR 2026. Congratulations to Xingyuan!
Publications * Corresponding author · # Co-first author
Conference Papers
- TIMA: Test-Time Internalization for Agentic Memory
Xiaohang Sui, Yongjian Fu, Yizhe Zhao, Sheng Yue, and Ju Ren
The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), Sydney, Australia, Dec 6–12, 2026. - Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy
Puning Zhao, Zhikun Zhang, Shaowei Wang, Sheng Yue, Bangzhou Xin, Tianhang Zheng, Pengfei Zhang, and Xiaochun Cao
ACM Conference on Computer and Communications Security (CCS), The Hague, the Netherlands, Nov 15–19, 2026. - AdamO: A Collapse-Suppressed Optimizer for Offline RL
Nan Qiao, Sheng Yue*, Shuning Wang, and Ju Ren
International Conference on Machine Learning (ICML), Seoul, South Korea, July 6–11, 2026. - Executable Agentic Memory for GUI Agent
Zerui Qin, Sheng Yue, Xingyuan Hua, Yongjian Fu, and Ju Ren
International Conference on Machine Learning (ICML), Seoul, South Korea, July 6–11, 2026. - Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization
Xingyuan Hua, Sheng Yue*, and Ju Ren
International Conference on Machine Learning (ICML), Seoul, South Korea, July 6–11, 2026. - Sparse Estimation Under Local Differential Privacy at All Privacy Levels
Puning Zhao, Qingqing Ye, Shaowei Wang, Jun Feng, Sheng Yue, Zhen Chen, and Xiaochun Cao
IEEE Symposium on Security and Privacy (SP), San Francisco, US, May 18–21, 2026. - Accelerating Graph-Based RAG Retrieval via Locality-Aware Device–Cloud Collaboration
Yongheng Deng, Tianyuan Jiang, Zhenya Ma, Hao Wu, Yongjian Fu, Hao Pan, Sheng Yue, and Ju Ren
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Jeju, South Korea, Aug 9–13, 2026. - Less Is More: Clustered Cross-Covariance Control for Offline RL
Nan Qiao, Sheng Yue*, Shuning Wang, Yongheng Deng, and Ju Ren
International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 23–27, 2026. - Context Learning for Multi-Agent Discussion
Xingyuan Hua, Sheng Yue*, Xinyi Li, Yizhe Zhao, Jinrui Zhang, and Ju Ren
International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 23–27, 2026. - RAG4DMC: Retrieval-Augmented Generation for Data-Level Modality Completion
Ningxin He, Yongheng Deng, Sheng Yue, Yongjian Fu, Zehui Zhang, and Tiegang Gao
International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 23–27, 2026. - FORLER: Federated Offline Reinforcement Learning with Q-Ensemble and Actor Rectification
Nan Qiao and Sheng Yue*
IEEE International Conference on Communications (ICC), Glasgow, UK, May 24–28, 2026. - FocusX: All-in-Focus Image Synthesis for Dynamic Scenes on Mobile Devices
Jinrui Zhang, Pengkai Li, Fengzu Li, Deyu Zhang, Wei Gao, Sheng Yue, Yaoxue Zhang, and Ju Ren
The 31st Annual International Conference on Mobile Computing and Networking (MobiCom), Hong Kong, China, Nov 4–8, 2025. - Towards Distance-Adaptive Wireless Charging
Lili Chen, Yizhe Zhao, Shuning Wang, Linghui Zhong, Yongjian Fu, Sheng Yue, Ju Ren, and Yaoxue Zhang
ACM International Conference on Mobile Systems, Applications, and Services (MobiSys), Anaheim, US, June 23–27, 2025. - How to Leverage Diverse Demonstrations in Offline Imitation Learning
Sheng Yue, Jiani Liu, Xingyuan Hua, Ju Ren, Sen Lin, Junshan Zhang, and Yaoxue Zhang
International Conference on Machine Learning (ICML), Vienna, Austria, July 21–27, 2024. - OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning
Sheng Yue, Xingyuan Hua, Ju Ren, Sen Lin, Junshan Zhang, and Yaoxue Zhang
International Conference on Machine Learning (ICML), Vienna, Austria, July 21–27, 2024. - Momentum-Based Federated Reinforcement Learning with Interaction and Communication Efficiency
Sheng Yue, Xingyuan Hua, Lili Chen, and Ju Ren
IEEE International Conference on Computer Communications (INFOCOM), Vancouver, Canada, May 20–23, 2024. - Federated Offline Policy Optimization with Dual Regularization
Sheng Yue, Zerui Qin, Xingyuan Hua, Yongheng Deng, and Ju Ren
IEEE International Conference on Computer Communications (INFOCOM), Vancouver, Canada, May 20–23, 2024. - BR-DeFedRL: Byzantine-Robust Decentralized Federated Reinforcement Learning with Fast Convergence and Communication Efficiency
Jing Qiao, Zuyuan Zhang, Sheng Yue*, Yuan Yuan, Zhipeng Cai, Xiao Zhang*, Ju Ren, and Dongxiao Yu
IEEE International Conference on Computer Communications (INFOCOM), Vancouver, Canada, May 20–23, 2024. - RelayRec: Empowering Privacy-Preserving CTR Prediction via Cloud-Device Relay Learning
Yongheng Deng, Guanbo Wang, Sheng Yue, Wei Rao, Qin Zu, Wenjie Wang, Shuai Chen, Ju Ren, and Yaoxue Zhang
ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), Hong Kong, China, May 13–16, 2024. - FedINC: An Exemplar-Free Continual Federated Learning Framework with Small Labeled Data
Yongheng Deng, Sheng Yue, Guanbo Wang, Tuowei Wang, Ju Ren, and Yaoxue Zhang
ACM Conference on Embedded Networked Sensor Systems (SenSys), Nov 13–15, Istanbul, Turkiye, 2023. - CLARE: Conservative Model-Based Offline Inverse Reinforcement Learning
Sheng Yue, Guanbo Wang, Wei Shao, Zhaofeng Zhang, Sen Lin, Ju Ren, and Junshan Zhang
International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 1–5, 2023. - HSFL: An Efficient Split Federated Learning Framework via Hierarchical Organization
Tengxi Xia, Yongheng Deng, Sheng Yue, Junyi He, Ju Ren, and Yaoxue Zhang
International Conference on Network and Service Management (CNSM), Thessaloniki, Greece, Oct 31–Nov 4, 2022. - Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning
Sheng Yue, Ju Ren, Jiang Xin, Sen Lin, and Junshan Zhang
ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc), Shanghai, China, July 26–29, 2021.
Journal Papers
- HyStream: A Hybrid System for Application Streaming via Predictive Delivery and Sequence-Linearized Caching
Jun Lu, Sheng Yue, Xiang Liu, Jinrui Zhang, Yongjian Fu, and Jialin Li
IEEE Transactions on Networking (ToN), vol. 34, pp. 5514–5529, 2026. - Toward Communication-Efficient and Data-Free Collaborative Fine-Tuning Between Small and Large Language Models
Zhenya Ma, Yongheng Deng, Ziqing Qiao, Yongjian Fu, Sheng Yue, and Ju Ren
IEEE Transactions on Networking (ToN), vol. 34, pp. 5333–5348, 2026. - Two-dimensional Stackelberg Game-based Incentive Mechanism for Differential Private Federated Learning with Non-IID Data
Dan Wang, Xiaoyi Pang, Jiahui Hu, Sheng Yue*, and Ju Ren
IEEE Transactions on Mobile Computing (TMC), early access, 2026. - 𝒪2-UCB: A Federated Multi-armed Bandit Mechanism in Zero Client-owned Data Network
Hangfan Li, Yang Xu, Yibin Cai, Sheng Yue, Ziyu Peng, and Yaoxue Zhang
IEEE Transactions on Mobile Computing (TMC), early access, 2026. - FOVA: Offline Federated Reinforcement Learning With Mixed-Quality Data
Nan Qiao, Sheng Yue*, Ju Ren, and Yaoxue Zhang
IEEE Transactions on Networking (ToN), vol. 34, pp. 2031–2046, 2026. - MASA: Multimodal Federated Learning through Modality-Aware and Secure Aggregation
Jialin Guo, Yongjian Fu, Zhiwei Zhai, Xinyi Li, Yongheng Deng, Sheng Yue, Lili Chen, Hao Pan, and Ju Ren
IEEE Transactions on Mobile Computing (TMC), vol. 24, no. 8, pp. 7328–7344, 2025. - AugFL: Augmenting Federated Learning with Pretrained Models
Sheng Yue#, Zerui Qin#, Yongheng Deng, Ju Ren, Yaoxue Zhang, and Junshan Zhang
IEEE Transactions on Networking (ToN), vol. 33, no. 4, pp. 1870–1885, 2025. - DualRec: A Collaborative Training Framework for Device and Cloud Recommendation Models
Ye Zhang, Yongheng Deng, Sheng Yue, Qiushi Li, and Ju Ren
IEEE Transactions on Mobile Computing (TMC), vol. 24, no. 6, pp. 5202–5213, 2025. - Momentum-Based Contextual Federated Reinforcement Learning
Sheng Yue#, Xingyuan Hua#, Yongheng Deng, Lili Chen, Ju Ren, and Yaoxue Zhang
IEEE Transactions on Networking (ToN), vol. 33, no. 2, pp. 865–880, 2025. - StreamSys: A Lightweight Executable Delivery System for Edge Computing
Jun Lu, Zhenya Ma, Yinggang Gao, Sheng Yue, Ju Ren, and Yaoxue Zhang
IEEE Transactions on Cloud Computing (TCC), vol. 13, no. 1, pp. 213–226, 2025. - MAML-RAL: Learning Domain-Invariant HOI Rules for Real-Time Video Matting
Jiang Xin, Sheng Yue*, Jinrui Zhang*, Ju Ren, Feng Qian, and Yaoxue Zhang
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 35, no. 4, pp. 3172–3184, 2025. - Federated Offline Reinforcement Learning with Proximal Policy Evaluation
Sheng Yue, Yongheng Deng, Guanbo Wang, Ju Ren, and Yaoxue Zhang
Chinese Journal of Electronics (CJE), vol. 33, no. 6, pp. 1–13, 2024. - Mobile Generative AI: Opportunities and Challenges
Ye Zhang, Jinrui Zhang*, Sheng Yue*, Wei Lu, Ju Ren, and Xuemin (Sherman) Shen
IEEE Wireless Communications (WC), vol. 31, no. 4, pp. 58–64, 2024. - Dependent Task Offloading in Edge Computing Using GNN and Deep Reinforcement Learning
Zequn Cao, Xiaoheng Deng, Sheng Yue, Ping Jiang, Ju Ren, and Jinsong Gui
IEEE Internet of Things Journal (IoTJ), vol. 11, no. 12, pp. 21632–21646, 2024. - SESAME: A Resource Expansion and Sharing Scheme for Multiple Edge Services Providers
Jiani Liu, Ju Ren, Yongmin Zhang, Sheng Yue, and Yaoxue Zhang
IEEE/ACM Transactions on Networking (ToN), vol. 32, no. 4, pp. 3189–3204, 2024. - PoPeC: PAoI-Centric Task Offloading with Priority over Unreliable Channels
Nan Qiao, Sheng Yue, Yongmin Zhang, and Ju Ren
IEEE/ACM Transactions on Networking (ToN), vol. 32, no. 3, pp. 2376–2390, 2024. - Towards Resource-Efficient Edge AI: From Federated Learning to Semi-Supervised Model Personalization
Zhaofeng Zhang, Sheng Yue*, and Junshan Zhang
IEEE Transactions on Mobile Computing (TMC), vol. 23, no. 5, pp. 6104–6115, 2024. - Efficient Federated Meta-Learning over Multi-Access Wireless Networks
Sheng Yue, Ju Ren, Jiang Xin, Deyu Zhang, Yaoxue Zhang, and Weihua Zhuang
IEEE Journal on Selected Areas in Communications (JSAC), vol. 40, no. 5, pp. 1556–1570, 2022. - TODG: Distributed Task Offloading with Delay Guarantees for Edge Computing
Sheng Yue, Ju Ren, Nan Qiao, Yongmin Zhang, Hongbo Jiang, Yaoxue Zhang, and Yuanyuan Yang
IEEE Transactions on Parallel and Distributed Systems (TPDS), vol. 33, no. 7, pp. 1650–1665, 2022. - Joint Channel Allocation and Resource Management for Stochastic Computation Offloading in MEC
Ju Ren, K. M. Mahfujul, Feng Lyu, Sheng Yue, and Yaoxue Zhang
IEEE Transactions on Vehicular Technology (TVT), vol. 69, no. 8, pp. 8900–8913, 2020. - Joint Channel Assignment and Stochastic Energy Management for RF-Powered OFDMA WSNs
Ju Ren, Sheng Yue, Deyu Zhang, Yaoxue Zhang, and Jiannong Cao
IEEE Transactions on Vehicular Technology (TVT), vol. 68, no. 2, pp. 1578–1592, 2019.
Books & Chapters
- Efficient Federated Meta-Learning over Multi-Access Wireless Networks
Sheng Yue, Ju Ren
Book Chapter of Next Generation Multiple Access, Wiley, 2023.
Grants
- 1/2026–12/2029
- NSFC
Research on End-Cloud Collaborative Computing for LLM-based Agents
Principal Investigator · National Natural Science Foundation of China (国家自然科学基金面上项目) - 1/2026–12/2028
- GDSTC
Research on Heterogeneity-Adaptive LLM-Based Edge Computing
Principal Investigator · Natural Science Foundation of Guangdong Province (广东省基础与应用基础研究基金自然科学基金面上项目) - 1/2026–12/2029
- SZSTI
Research on Heterogeneity-Adaptive Construction and Decision-Making for Mobile Agents
Principal Investigator · Natural Science Foundation of Shenzhen (深圳市自然科学基金面上项目) - 1/2024–12/2024
- NSFC
Research on Offline Federated Reinforcement Learning without Environmental Interaction
Principal Investigator · Young Scientists Fund of NSFC (国家自然科学基金青年科学基金) - 1/2024–12/2024
- CPSF
Research on Privacy-Preserving Distributed Offline Federated Reinforcement Learning
Principal Investigator · General Fund of CPSF (中国博士后科学基金面上资助) - 1/2024–12/2024
- CPSF
Distributed Offline Policy Optimization under Limited Samples and Heterogeneous Environments
Principal Investigator · Postdoctoral Fellowship Program of CPSF (国家资助博士后研究人员计划项目) - 8/2022–8/2023
- Industrial Project
Application of Edge Intelligence in the Hotel and Travel Business
Co-Principal Investigator · Tsinghua-Meituan Cooperation and Development Project (清华-美团技术合作开发项目) - 7/2022–6/2024
- Industrial Project
Multi-Satellite Collaborative Intelligent Computing Key Technology R&D
Co-Principal Investigator · Aerospace Hongtu Core R&D Project (航天宏图核心研发委托项目) - 9/2024–9/2025
- Industrial Project
Atomic Scene Recognition Technology R&D
Co-Principal Investigator · Tsinghua-Honor Cooperation and Development Project (清华-荣耀技术合作开发项目) - 1/2025–12/2029
- NSFC
Research on Edge-Cloud Collaborative Computing for Large Models with Heterogeneous End Devices
Key Member (Ranked First) · Key Program of NSFC (国家自然科学基金重点项目) - 12/2019–12/2024
- MOST
Probe Computer Software System Development
Key Member · National Key R&D Program of China (国家重点研发计划) - 10/2022–9/2025
- MOST
Research of Intelligent Computing Key Standards for Heterogeneous Devices
Key Member · National Key R&D Program of China (国家重点研发计划) - 11/2022–10/2025
- MOST
Blockchain-based Trusted Sharing Technology and Demonstration Application for Health Data
Key Member · National Key R&D Program of China (国家重点研发计划) - 1/2021–12/2023
- NSFC
Research on Edge Server Deployment and Resource Allocation Optimization
Key Member · General Program of NSFC (国家自然科学基金面上项目)
Honors & Service
Awards
- ACM China SIGAPP Rising Star Award, 2026
- Young Elite Scientists Sponsorship Program of CAST, 2025
- CIE Doctoral Dissertation Incentive Program, 2024
- ACM China SIGAPP Doctoral Dissertation Award, 2023
- Postdoctoral Fellowship Program of CPSF, 2023
Academic Service
- Area Editor, Chinese Journal of Electronics
- Executive Committee Member, CCF Technical Committee on IoT
- Area Chair, ICLR 2026
- Co-Chair, Edge Intelligence Track, ICPADS 2026
- TPC Member, IEEE MSN 2025 and IEEE MSN 2024
- Session Chair, ICCC 2023
Invited Reviewer
- IEEE/ACM Transactions on Networking
- IEEE Journal on Selected Areas in Communications
- IEEE Transactions on Parallel and Distributed Systems
- IEEE Transactions on Mobile Computing
- IEEE Transactions on Cloud Computing
- IEEE Transactions on Vehicular Technology
- Chinese Journal of Electronics
- ICML (2024–), ICLR (2022–), NeurIPS (2022–)
Teaching
- CSE101: Computer Programming I
Undergraduate Course, Fall 2025 / Fall 2026 - DCS5001: Introduction to Artificial Intelligence
Graduate Course, Spring 2025
Talks
- Design of Offline Reinforcement Learning Algorithms, Frontiers of Cyber Science and Technology, School of Cyber Science and Technology, Sun Yat-sen University, Apr 2024.
- Momentum-Based Federated Reinforcement Learning with Interaction and Communication Efficiency, IEEE INFOCOM 2024, Vancouver, Canada, May 2024.
- Federated Offline Policy Optimization with Dual Regularization, IEEE INFOCOM 2024, Vancouver, Canada, May 2024.
- Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning, ACM MobiHoc 2021, Shanghai, China, Jul 2021.