Zhenyi Wang

7

Papers

39

Total Citations

Papers (7)

A Unified and General Framework for Continual Learning

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

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

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

FREE: Faster and Better Data-Free Meta-Learning