Wang, Zhenyi
30 publications
TMLR
2026
AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective
NeurIPS
2025
Adaptive Defense Against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
ICML
2024
Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications
ICML
2024
Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-Trained Models