Zhenyi Wang

15

Papers

39

Total Citations

Papers (15)

A Unified and General Framework for Continual Learning

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications

Defense against Model Extraction Attack by Bayesian Active Watermarking

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models

Representation Surgery for Multi-Task Model Merging

MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation

Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning

Meta Learning on a Sequence of Imbalanced Domains With Difficulty Awareness

Data Augmented Flatness-aware Gradient Projection for Continual Learning

Meta-Learning with Less Forgetting on Large-Scale Non-stationary Task Distributions

Learning To Learn and Remember Super Long Multi-Domain Task Sequence

FREE: Faster and Better Data-Free Meta-Learning

Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training

An Efficient Dataset Condensation Plugin and Its Application to Continual Learning