← back to search

Li Shen

Sun Yat-sen University · CN
Area of research
Artificial Intelligence · Computer Vision and Pattern Recognition
Research interest
Research interests include Privacy-Preserving Technologies in Data, Domain Adaptation and Few-Shot Learning, Stochastic Gradient Optimization Techniques, and Advanced Neural Network Applications.
h-index
42
citations
7,947
works
332
NIH funding
primary concept
email

Recent publications

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications, and Opportunities
ACM Computing Surveys 2026cited by 12position: contributordoi
FreeStyle: Free lunch for text-guided style transfer using diffusion models
Pattern Recognition 2026cited by 4position: contributordoi
Deep Model Fusion: A Survey.
2026cited by 3position: contributordoi
Communication Learning in Multi-Agent Systems From Graph Modeling Perspective
IEEE Transactions on Knowledge and Data Engineering 2026cited by 3position: contributordoi
Probability-Guided Contrastive Learning for Long-Tailed Domain Generalization
IEEE Transactions on Big Data 2026cited by 2position: contributordoi
Prodigal: Backdoor defense for federated learning beyond robust aggregation
Knowledge-Based Systems 2026cited by 1position: contributordoi
Toward Understanding Generalization and Stability Gaps Between Centralized and Decentralized Federated Learning.
2026cited by 0position: contributordoi
Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration
IEEE Transactions on Pattern Analysis and Machine Intelligence 2026cited by 0position: contributordoi
Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
IEEE Transactions on Pattern Analysis and Machine Intelligence 2026cited by 0position: contributordoi
Adaptive Batch Size Time Evolving Stochastic Gradient Descent for Federated Learning.
2026cited by 0position: contributordoi
Task-Distributionally Robust Data-Free Meta-Learning.
2026cited by 0position: contributordoi
Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models.
2026cited by 0position: contributordoi
Towards understanding memory buffer based continual learning.
2026cited by 0position: contributordoi
Instructed Diffuser With Temporal Condition Guidance for Offline Reinforcement Learning.
2026cited by 0position: contributordoi
Release the Potential of Memory Buffer in Continual Learning: A Dynamic System Perspective.
2026cited by 0position: contributordoi
Decentralized Federated Learning With Period Gradient Tracking Over Time-Varying Networks
IEEE Transactions on Parallel and Distributed Systems 2026cited by 0position: contributordoi
Curiosity-driven cooperation for long-tailed multi-label learning
Neural Networks 2026cited by 0position: contributordoi
<tt>AlphaDecay</tt> : Module-Wise Weight Decay for Heavy-Tailed Balancing in LLMs
International Journal of Artificial Intelligence and Robotics Research 2026cited by 0position: contributordoi
Teleportation: Defense Against Stealing Attacks of Data-Driven Healthcare APIs
IEEE Transactions on Artificial Intelligence 2026cited by 0position: contributordoi
Decentralized Partial Model Personalization With Guaranteed Nonconvex Convergence
IEEE Transactions on Networking 2026cited by 0position: contributordoi
EEformer: Early Exiting for Transformer With Global-Local Exits and Progressive Fine-Tuning
IEEE Transactions on Multimedia 2026cited by 0position: contributordoi
Learning from models beyond fine-tuning
Nature Machine Intelligence 2025cited by 59position: contributordoi
Learning from models beyond fine-tuning
Nature Machine Intelligence 2025cited by 55position: middledoi
Graph Convolutional Mixture-of-Experts Learner Network for Long-Tailed Domain Generalization
IEEE Transactions on Circuits and Systems for Video Technology 2025cited by 6position: contributordoi
AdaptiveFL: Communication-Adaptive Federated Learning Under Dynamic Bandwidth
IEEE Transactions on Neural Networks and Learning Systems 2025cited by 4position: lastdoi
Sequential Federated Learning in Hierarchical Architecture on Non-IID Datasets
IEEE Transactions on Mobile Computing 2025cited by 3position: contributordoi
A Pyramid Fusion MLP for Dense Prediction.
2025cited by 2position: contributordoi
Dynamic Analysis and Adaptive Discriminator for Fake News Detection
Proceedings of the 33rd ACM International Conference on Multimedia 2025cited by 2position: contributordoi
Targeted Vaccine: Safety Alignment for Large Language Models Against Harmful Fine-Tuning via Layer-Wise Perturbation
IEEE Transactions on Information Forensics and Security 2025cited by 2position: contributordoi
DFedGFM: Pursuing global consistency for Decentralized Federated Learning via global flatness and global momentum.
2025cited by 1position: contributordoi

Grants

No grants ingested yet.

Frequent collaborators

· 85 papers (2020–2026)Dacheng Tao · Nanyang Technological University26 papers (2023–2026)Han Hu · Beijing Institute of Technology, China14 papers (2023–2026)Yong Luo · Wuhan University13 papers (2023–2026)Zhenyi Wang · University of Maryland, College Park9 papers (2023–2026)Nan Yin · Elsevier, Inc.8 papers (2023–2026)Xiaochun Cao · Sun Yat-sen University7 papers (2025–2026)Dacheng Tao · The University of Sydney7 papers (2023–2025)Enneng Yang · Sun Yat-sen University7 papers (2024–2026) · 7 papers (2025–2026)Bo Du · Wuhan University7 papers (2023–2026)Wei Liu · Stanford University7 papers (2022–2024)Liang Ding · The University of Sydney6 papers (2023–2026)Guibing Guo · Northeastern University6 papers (2024–2026)Liang Ding · Harbin Institute of Technology4 papers (2023–2024)Weiwei Lin · South China University of Technology4 papers (2022–2026)Guozhi Liu · South China University of Technology4 papers (2025–2026)Yonggang Wen · Chinese University of Hong Kong4 papers (2025–2025)Xiao Luo · University of Wisconsin–Madison4 papers (2023–2025)Tongliang Liu · University of Sydney4 papers (2024–2026)