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.
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications, and Opportunities
FreeStyle: Free lunch for text-guided style transfer using diffusion models
Deep Model Fusion: A Survey.
Communication Learning in Multi-Agent Systems From Graph Modeling Perspective
Probability-Guided Contrastive Learning for Long-Tailed Domain Generalization
Prodigal: Backdoor defense for federated learning beyond robust aggregation
Toward Understanding Generalization and Stability Gaps Between Centralized and Decentralized Federated Learning.
Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration
Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
Adaptive Batch Size Time Evolving Stochastic Gradient Descent for Federated Learning.
Task-Distributionally Robust Data-Free Meta-Learning.
Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models.
Towards understanding memory buffer based continual learning.
Instructed Diffuser With Temporal Condition Guidance for Offline Reinforcement Learning.
Release the Potential of Memory Buffer in Continual Learning: A Dynamic System Perspective.
Decentralized Federated Learning With Period Gradient Tracking Over Time-Varying Networks
Curiosity-driven cooperation for long-tailed multi-label learning
<tt>AlphaDecay</tt>
: Module-Wise Weight Decay for Heavy-Tailed Balancing in LLMs
Teleportation: Defense Against Stealing Attacks of Data-Driven Healthcare APIs
Decentralized Partial Model Personalization With Guaranteed Nonconvex Convergence
EEformer: Early Exiting for Transformer With Global-Local Exits and Progressive Fine-Tuning
Learning from models beyond fine-tuning
Learning from models beyond fine-tuning
Graph Convolutional Mixture-of-Experts Learner Network for Long-Tailed Domain Generalization
AdaptiveFL: Communication-Adaptive Federated Learning Under Dynamic Bandwidth
Sequential Federated Learning in Hierarchical Architecture on Non-IID Datasets
A Pyramid Fusion MLP for Dense Prediction.
Dynamic Analysis and Adaptive Discriminator for Fake News Detection
Targeted Vaccine: Safety Alignment for Large Language Models Against Harmful Fine-Tuning via Layer-Wise Perturbation
DFedGFM: Pursuing global consistency for Decentralized Federated Learning via global flatness and global momentum.