Yihua Zhang

papers

857

total citations

papers (13)

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

ICLR 2024arXiv

284

citations

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

ICML 2024arXiv

107

citations

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

ICML 2025arXiv

citations

Robust Mixture-of-Expert Training for Convolutional Neural Networks

ICCV 2023arXiv

citations

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

AAAI 2025arXiv

citations

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free

CVPR 2022arXiv

citations

Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning

NEURIPS 2023arXiv

citations

Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

CVPR 2025arXiv

citations

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design

ICCV 2025arXiv

citations

Yihua Zhang

papers (13)

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

Understanding and Improving Visual Prompting: A Label-Mapping Perspective

Advancing Model Pruning via Bi-level Optimization

DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training

Fairness Reprogramming

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

Robust Mixture-of-Expert Training for Convolutional Neural Networks

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free

Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning

Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design

papers (13)

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

Understanding and Improving Visual Prompting: A Label-Mapping Perspective

Advancing Model Pruning via Bi-level Optimization

DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training

Fairness Reprogramming

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

Robust Mixture-of-Expert Training for Convolutional Neural Networks

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free

Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning

Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design