Dr. Ye Shi received the Ph.D. degree at the University of Technology Sydney (UTS), Australia in 2018. Dr Shi served as a Research Assistant at the University of New South Wales, Australia from 2017 to 2019, and a Postdoctoral Fellow at the University of Technology Sydney from 2019 to 2020. Dr. Shi has been an Assistant Professor (PI) in the School of Information Science and Technology at ShanghaiTech University since January 2021.

✡️ Research Interests

  • Embodied AI: reliable generative models, open-world 3D perception, safe decision-making and control;

  • Federated Learning: heterogeneity, personalization, generalization, robustness, pre-trained models;

  • Basics for Deep Learning: implicit differentiation, optimization layer, deep equilibrium models, convergence and generalization analysis, learning with noise;

  • AI for Energy: learning to optimize and control, safe reinforcement learning, distributed decision-making, and control with uncertainties.

🔊 Position Openings

  • Postgraduate Students: Dr. Ye Shi recruits 2~3 postgraduate students for each academic year. The candidate is expected to be self-motivated in one of the following areas: Artificial Intelligence, Machine learning, 3D Vision, Smart Energy, etc. A solid mathematical background and sufficient programming skills are required. If you are interested in this opening, please email me your CV;
  • Undergraduates/Visting Students: We warmly welcome students (from ShanghaiTech or other Universities) majored in Machine Learning, Computer Science, Mathematics, Electric Engineering, Information and Communication Engineering, and other related disciplines to join our group;
  • Research Assistant: Dr. Ye Shi is seeking a research assistant to work closely with the principal investigator, postdoc, and students in the laboratory. A Bachelor’s or master’s degree in mathematics, computer science, machine learning, electrical engineering, control, or related areas is required.

🔥 News

  • 2024.5: Two Papers accepted by ICML 2024. Congratulations to Lingxiao Yang and Tianyu Cui.
  • 2024.3: I gave a talk at The 1st China Embodied AI Conference: “Model-Data Hybrid-Driven Embodied Agents: Fundamentals and Applications”.
  • 2024.3: Our Paper “A Distributionally Robust Model Predictive Control for Static and Dynamic Uncertainties in Smart Grids” has been accepted by IEEE Trans. Smart Grid. Congratulations to Qi Li! (This paper was submitted when Qi Li was still an undergraduate student.)
  • 2024.2: Three Papers accepted by CVPR 2024.
  • 2024.1: Our Paper “Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory” has been accepted by ICLR 2024.
  • 2023.12: Two Papers accepted by AAAI 2024.
  • 2023.11: I gave a talk at RLChina 2023: “Towards Responsible Decision and Control via Implicit Networks”.
  • 2023.09: Five Papers accepted by NeurIPS 2023.
  • 2023.10: Our students Shutong Ding, Tianyu Cui, Wanxing Chang and Chunlin Yu received the NeurIPS 2023 Scholar Award. Big Congratulations!
  • 2023.09: “Reduced Policy Optimization for Continuous Control with Hard Constraints” has been accepted by NeurIPS 2023. Congratulations to Shutong Ding!
  • 2023.09: “Two Sides of The Same Coin: Bridging Deep Equilibrium Models and Neural ODEs via Homotopy Continuation” has been accepted by NeurIPS 2023. Congratulations to Shutong Ding and Tianyu Cui!
  • 2023.09: “CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels” has been accepted by NeurIPS 2023. Congratulation to Wanxing Chang!
  • 2023.09: “Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning” has been accepted by NeurIPS 2023. Congratulations to Zhongyi Cai!
  • 2023.09: “Contextually Affinitive Neighborhood Refinery for Deep Clustering” has been accepted by NeurIPS 2023. Congratulations to Chunlin Yu!
  • 2023.04: “FedTP: Federated Learning by Transformer Personalization” has been accepted by IEEE Transactions on Neural Networks and Learning Systems, 2023. (Impact factor 14.225) Congratulations to Hongxia Li and Zhongyi Cai!
  • 2023.03: “NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions” has been accepted by CVPR 2023 (CCF A). Congratulations to Juze Zhang!
  • 2023.01: “Robust Fuzzy Neural Network with an Adaptive Inference Engine” has been accepted by IEEE Transactions on Cybernetics, 2023. (Impact factor 19.118) Congratulations to Leijie Zhang!
  • 2023.01: “Alternating Differentiation for Optimization Layers” has been accepted by ICLR 2023 (Core A). Congratulations to Haixiang Sun!
  • 2022.11: “IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation” has been accepted by AAAI 2023 (CCF A) as an Oral. Congratulations to Juze Zhang!
  • 2022.11: “Beyond Rehearsal: Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation” has been accepted by AAAI 2023 (CCF A) as an Oral. Congratulations to Chunlin Yu!
  • 2022.10: “Distributionally Robust Optimization for Vehicle-to-grid with Uncertain Renewable Energy” has been accepted by ICCAIS 2022 as an oral. The first author is our undergraduate student Qi Li. Congratulations!
  • 2022.09: “Unified Optimal Transport Framework for Universal Domain Adaptation” has been accepted by NeurIPS 2022 (CCF A) as a Spotlight. Congratulation to Wanxing Chang!
  • 2022.09: “Federated Fuzzy Neural Networks with Evolutionary Rule Learning” has been accepted by IEEE Transactions on Fuzzy Systems. (Impact factor 12.029) Congratulations to Leijie Zhang!
  • 2022.07: “Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation” has been accepted by ACM Multimedia 2022 (CCF A). Congratulations to Juze Zhang!
  • 2021.12: One paper (Corresponding author) received the Best Student Paper Award at the Australia Artificial Intelligence Institute.
  • 2021.08: One paper has been accepted by IEEE Transactions on Fuzzy Systems. (Impact factor 12.029)
  • 2021.07: One paper (First author) has been accepted by IEEE Transactions on Fuzzy Systems. (Impact factor 12.029)
  • 2021.05: One paper (First author) has been published in Applied Energy. (Impact factor 9.746)
  • 2021.04: One paper has been published in IEEE Transactions on Multimedia. (Impact Factor 6.051)
  • 2021.01: Dr. Ye Shi joined ShanghaiTech as a Tenure-track Assistant Professor.

📝 Selected Publications

ICML 2024
sym

Guidance with Spherical Gaussian Constraint for Conditional Diffusion, ICML 2024

Lingxiao Yang, Shutong Ding, Yifan Cai, Jingyi Yu, Jingya Wang, Ye Shi*

ICML 2024
sym

Harmonizing Generalization and Personalization in Federated Prompt Learning, ICML 2024

Tianyu Cui, Hongxia Li, Jingya Wang, Ye Shi*

CVPR 2024
sym

Global and Local Prompts Cooperation via Optimal Transport for Federated Learning, CVPR 2024

Hongxia Li, Wei Huang, Jingya Wang, Ye Shi*

CVPR 2024
sym

$\text{S}^2$Fusion: A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals, CVPR 2024

Jiangnan Tang, Jingya Wang, Kaiyang Ji, Lan Xu, Jingyi Yu, Ye Shi*

CVPR 2024
sym

HOI-M$^3$: Capture Multiple Humans and Objects Interaction within Contextual Environment, CVPR 2024

Juze Zhang, Jingyan Zhang, Zining Song, Zhanhe Shi, Chengfeng Zhao, Ye Shi, Jingyi Yu, Lan Xu, Jingya Wang*

ICLR 2024
sym

Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory, ICLR 2024

Wei Huang, Ye Shi, Zhongyi Cai, Taiji Suzuki

AAAI 2024
sym

Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport, AAAI 2024

Bin Li, Ye Shi, Qian Yu, Jingya Wang

AAAI 2024
sym

HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations, AAAI 2024

Yilan Dong, Chunlin Yu, Ruiyang Ha, Ye Shi, Yuexin Ma, Lan Xu, Yanwei Fu, Jingya Wang

NeurIPS 2023
sym

Reduced Policy Optimization for Continuous Control with Hard Constraints, NeurIPS 2023

Shutong Ding, Jingya Wang, Yali Du, Ye Shi*

NeurIPS 2023
sym

Two Sides of The Same Coin: Bridging Deep Equilibrium Models and Neural ODEs via Homotopy Continuation, NeurIPS 2023

Shutong Ding#, Tianyu Cui#, Jingya Wang, Ye Shi*

NeurIPS 2023
sym

CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels, NeurIPS 2023

Wanxing Chang, Ye Shi, Jingya Wang

NeurIPS 2023
sym

Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning, NeurIPS 2023

Zhongyi Cai, Ye Shi*, Wei Huang, Jingya Wang

NeurIPS 2023
sym

Contextually Affinitive Neighborhood Refinery for Deep Clustering, NeurIPS 2023

Chunlin Yu, Ye Shi, Jingya Wang

ICCV 2023
sym

Knowledge-Aware Federated Active Learning with Non-IID Data, ICCV, 2023

Yu-Tong Cao, Ye Shi, Jingya Wang, Baosheng Yu, Dacheng Tao

[paper] [code]

IJCAI 2023
sym

StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset, IJCAI, 2023

Chaofan Huo, Ye Shi, Yuexin Ma, Lan Xu, Jingyi Yu, Jingya Wang

[paper] [project] [code]

IEEE TNNLS 2023
sym

FedTP: Federated Learning by Transformer Personalization, IEEE Transactions on Neural Networks and Learning Systems, 2023

Hongxia Li#, Zhongyi Cai#, Jingya Wang, Jiangnan Tang, Weipng Ding, Chin-Teng Lin, Ye Shi*

[paper] [code]

CVPR 2023
sym

NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions, CVPR 2023

Juze Zhang, Haimin Luo, Hongdi Yang, Xinru Xu, Qianyang Wu, Ye Shi, Jingyi Yu, Lan Xu*, Jingya Wang*

[paper] [project] [video]

IEEE Transactions on Cybernetics 2023
sym

Robust Fuzzy Neural Network with an Adaptive Inference Engine, IEEE Transactions on Cybernetics, 2023

Leijie Zhang, Ye Shi*, Yu-Cheng Chang and Chin-Teng Lin*

[paper] [code]

ICLR 2023
sym

Alternating Differentiation for Optimization Layers, ICLR 2023

Haixiang Sun, Ye Shi*, Jingya Wang, Hoang Duong Tuan, H.V. Poor, Dacheng Tao

[paper] [code]

AAAI 2023 (oral)
sym

IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation, AAAI 2023 (oral)

Juze Zhang, Ye Shi*, Yuexin Ma, Lan Xu, Jingyi Yu, Jingya Wang*

[paper] [project] [code]

AAAI 2023 (oral)
sym

Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation, AAAI 2023 (oral)

Chunlin Yu, Ye Shi, Zimo Liu, Shenghua Gao, Jingya Wang*

[paper] [project] [code]

NeurIPS 2022 (Spotlight)
sym

Unified Optimal Transport Framework for Universal Domain Adaptation, NeurIPS 2022 (Spotlight)

Wanxing Chang, Ye Shi*, Jingya Wang*, Hoang Duong Tuan

[paper] [project] [code] [video] [VALSE]

IEEE Transactions on Fuzzy Systems 2022
sym

Federated Fuzzy Neural Networks with Evolutionary Rule Learning, IEEE Transactions on Fuzzy Systems, 2022

Leijie Zhang, Ye Shi*, Yu-Cheng Chang and Chin-Teng Lin*

[paper] [code]

ACM MM 2022
sym

Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation, ACM MM 2022

Juze Zhang, Jingya Wang*, Ye Shi*, Lan Xu, Fei Gao, Jingyi Yu

[paper]

IEEE Transactions on Fuzzy Systems 2022
sym

Distributed Semi-supervised Fuzzy Regression with Interpolation Consistency Regularization, IEEE Transactions on Fuzzy Systems, 2022

Ye Shi#, Leijie Zhang#, Zehong Cao, M. Tanveer and Chin-Teng Lin*

[paper] [code]

  • Distributionally Robust Optimization for Vehicle-to-grid with Uncertain Renewable Energy, Qi Li#, Pengchao Tian#, Ye Shi*, Yuanming Shi and Hoang Duong Tuan, ICCAIS 2022 (Oral). [paper]

  • Distributed model predictive control for joint coordination of demand response and optimal power flow with renewables in smart grid, Ye Shi*, Hoang Duong Tuan, Andrey V. Savkin, Chin-Teng Lin, Jian Guo Zhu, H. Vincent Poor, Applied Energy, 2021. [paper]

  • Hierarchical fuzzy neural networks with privacy preservation on heterogeneous big data, Leijie Zhang#, Ye Shi#*, Yu-Cheng Chang, and Chin-Teng Lin, IEEE Transactions on Fuzzy Systems, 2021. [paper] [code]

  • PMU Placement Optimization for Efficient State Estimation in Smart Grid, Ye Shi, Hoang Duong Tuan*, Trung Q. Duong, H. Vincent Poor and Andrey V. Savkin, IEEE Journal on Selected Areas in Communications, 2020. [paper]

  • Parameterized bilinear matrix inequality techniques for H ∞ gain-scheduling proportional integral derivative control design, Ye Shi, Hoang Duong Tuan* and Pierre Apkarian, International Journal of Robust and Nonlinear Control, 2020. [paper]

  • Consensus learning for distributed fuzzy neural network in big data environment, Ye Shi*, Chin-Teng Lin, Yu-Cheng Chang, Weiping Ding, Yuhui Shi and Xin Yao, IEEE Transactions on Emerging Topics in Computational Intelligence, 2021. [paper]

  • Deep- IRTarget: An Automatic Target Detector in Infrared Imagery using Dual-domain Feature Extraction and Allocation, Ruiheng Zhang, Lixin Xu, Zhengyu Yu, Ye Shi, Chengpo Mu, Min Xu*, IEEE Transactions on Multimedia, 2021. [paper]

  • Interpretable Fuzzy Logic Control for Multi-Robot Coordination in a Cluttered Environment, Yu-Cheng Chang, Ye Shi, Anna Dostovalova, Zehong Cao, Chin-Teng Lin*, Daniel Gibbons, Jijoong Kim, IEEE Transactions on Fuzzy Systems, 2021. [paper]

  • Mixed integer nonlinear programming for Joint Coordination of Plug-in Electrical Vehicles Charging and Smart Grid Operations, Ye Shi*, Hoang Duong Tuan, and Andrey V. Savkin, the 10th IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, 2019. [paper]

  • Model Predictive Control for Smart Grids with Multiple Electric-Vehicle Charging Stations, Ye Shi, Hoang Duong Tuan, Andrey V. Savkin, Trung Q. Duong* and H. Vincent Poor, IEEE Transaction on Smart Grid, 2019. [paper]

  • Optimal Power Flow over Large-Scale Transmission Networks, Ye Shi, Hoang Duong Tuan*, Andrey V. Savkin, Steven W. Su, Systems & Control Letters, 2018. [paper]

  • Nonconvex Spectral Optimization Algorithms for Reduced-Order H∞ LPV-LFT controllers, Ye Shi, Hoang Duong Tuan* and Pierre Apkarian, International Journal of Robust and Nonlinear Control, 2017. [paper]

  • Global Optimization for Optimal Power Flow over Transmission Networks, Ye Shi, Hoang Duong Tuan* , Hoang Tuy and Steven W. Su, Journal of Global Optimization, 2017. [paper]

  • Nonconvex Spectral Algorithm for Solving BMI on the Reduced Order H∞ Control, Ye Shi*, Hoang Duong Tuan, and Steven W. Su, accepted by the 6th IEEE International Conference on Control Systems, Computing and Engineering, 2016. (Best Paper Award) [paper]
  • Nonsmooth Optimization for Optimal Power Flow over Transmission Networks, Ye Shi*, Hoang Duong Tuan, Steven W. Su and H. H. M. Tam, accepted by the 3rd IEEE Global Conference on Signal and Information Processing, 2015. [paper]

📖 Educations

  • 2014.02 - 2018.11, Ph.D., University of Technology Sydney, NSW, Australia.
  • 2009.09 - 2013.06, B.S., Northwestern Polytechnical University, Xi’an, China.

💻 Work Experience

  • Tenure-track Assistant Professor (2021.01 -now): School of Information Science and Technology, ShanghaiTech University.
  • Postdoctoral Fellow (2019.07-2020.12):
    • Australian Artificial Intelligence Institute, School of Computer Science, University of Technology Sydney.
    • Supervisor: Prof. Chin-Teng Lin (IEEE Fellow), E-mail: chin-teng.lin@uts.edu.au.
  • Research Assistant (2017.03-2019.06):
    • School of Electrical Engineering and Telecommunications, Faculty of Engineering, University of New South Wales.
    • Supervisor: Prof. Andrey V. Savkin, E-mail: a.savkin@unsw.edu.au

🎖️ Awards

  • 2024 My students received the NeurIPS 2023 Scholar Award.
  • 2021 Best Student Paper Award (Corresponding author) at Australia Artificial Intelligence Institute.
  • 2019 Outstanding Overseas Students Award, Chinese Ministry of Education, Australia. (A total of 500 people worldwide while only 50 people in Australia).
  • 2018 FEIT PhD Post Thesis Publication Award, University of Technology Sydney 2018, Australia.
  • 2017 Higher Degree Research Publication Award, University of Technology Sydney, Australia.
  • 2016 Best Paper Award, the 6th IEEE International Conference on Control Systems, Computing and Engineering, Malaysia.
  • 2016 ARC Discovery Scholarship, the University of Technology Sydney, 2014-2016, Australia.
  • 2016 International Research Scholarships, University of Technology Sydney, 2014-2016, Australia.
  • 2013 Meritorious Winner of the Interdisciplinary Contest in Modeling (ICM), The Society for Industrial and Applied Mathematics, America.
  • 2012 First Prize of Chinese Undergraduate Mathematical Contest for Modeling (CUMCM), China Society for Industrial and Applied Mathematics, China.
  • 2010 National Scholarship, Chinese Ministry of Education, China.

💬 Talks

  • 2023.11, Towards Responsible Decision and Control via Implicit Networks, RLChina 2023.
  • 2019.10, Joint Coordination of Plug-in Electrical Vehicles Charging and Smart Grid Operations, IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, Beijing.
  • 2018.04, Nonconvex and nonsmooth optimization in smart grids, International Forum for Interdisciplinary Sciences and Engineering Open Forum, Wuhan University.
  • 2016.11, Nonconvex Spectral Algorithm for Solving BMI on the Reduced Order H∞ Control, IEEE International Conference on Control Systems, Computing and Engineering, Penang, Malaysia.

🕴️ Activities

  • Session Chair The 10th IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm 2019).
  • Program committee
    • NeurIPS 2023, AAAI 2023, AAAI 2024, CVPR 2024, ICLR 2024.
  • Reviewer
    • IEEE Transactions on Neural Networks and Learning Systems
    • IEEE Transactions on Image Processing
    • IEEE Journal on Selected Areas in Communications
    • IEEE Transactions on Fuzzy System
    • IEEE Transactions on Smart Grid
    • IEEE Transactions on Power System
    • IEEE Transactions on Sustainable Energy
    • IEEE Transactions on Industrial Informatics
    • IEEE Transactions on Industrial Electronics
    • IEEE Transactions on Intelligent Vehicles
    • IEEE Transactions on Instrumentation & Measurement
    • IEEE Journal of Biomedical and Health Informatics
    • IEEE/CAA Journal of Automatica Sinica
    • IEEE Systems Journal
    • International Journal of Robust and Nonlinear Control
    • Information Sciences
    • Applied Soft Computing

🧑‍🏫 Teaching

  • Course SI251 - Convex Optimization, ShanghaiTech University, 2021 Spring, 2021 Autumn, 2022 Autumn.
  • Course SI152 - Numerical Optimization, ShanghaiTech University, 2022 Spring, 2023 Spring.

🧑‍🎓 Group

  • Ph.D. Students
    • Bikang Pan (2023 Fall - present): B.E. at ShanghaiTech University.
    • Jiebao Zhang (2023 Fall - present): M.S. at Yunnan University.
  • Master Students
    • Haixiang Sun (2021 Fall - present): B.S. at Beijing Forestry University, Outstanding Graduate in Beijing.
    • Pengchao Tian (2021 Fall - present): B.E. at ShanghaiTech University.
    • Hongxia Li (2021 Fall - present): B.S. at Nanjing University of Science and Technology.
    • Wanxing Chang (2021 Fall - present, jointly with Jingya Wang): B.E. at the University of Electronic Science and Technology of China.
    • Zhongyi Cai (2021 Fall - present, jointly with Jingya Wang): B.E. at ShanghaiTech University.
    • Shutong Ding (2022 Fall - present): B.E. at Fuzhou University.
    • Xinru Xu (2022 Fall - present): B.E. at ShanghaiTech University.
    • Tianyu Cui (2022 Fall - present): B.S. at the University of Science and Technology of China.
    • Jiangnan Tang (2022 Fall - present): B.E. at Beijing University of Posts and Telecommunications.
    • Lingxiao Yang (2023 Fall - present): B.E. at Northeastern University.
    • Haoyu Yan (2023 Fall - present): B.E. at Wuhan University of Technology.
    • Zichen Jin (2023 Fall - present): B.E. at Northeastern University.
  • Visiting Students
    • Qi Li (2022 Spring - present): B.S. in Applied Mathematics, ShanghaiTech University; M.S. in Applied Mathematics, Johns Hopkins University.