Yihua Zhang

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning

CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification

When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers

The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning

UOE: Unlearning One Expert is Enough for Mixture-of-Experts LLMs

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification

Visual Prompting Reimagined: The Power of Activation Prompts