Zixuan Hu

7

Papers

9

Total Citations

Papers (7)

LEAD: Exploring Logit Space Evolution for Model Selection

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

Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts

LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs

FREE: Faster and Better Data-Free Meta-Learning

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

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