Yihua Zhang
28 papers · 2022–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🌍 Conference Polyglot (10) 🐝 Cross-Pollinator (12) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌈 Renaissance Researcher (7)
🧭
Keyword Pioneer
🌈
Renaissance Researcher
(7)
🏆
Grand Slam
👑
Triple Crown
🤝
Dynamic Duo
(27)
💎
Century Club
(27)
⚡
Prolific Year
(6)
🗃️
Keyword Collector
(99)
❓
The Questioner
(4)
Conferences
NIPS (6)
ICLR (5)
ICML (5)
CVPR (3)
ACL (2)
EMNLP (2)
ICCV (2)
AAAI (1)
ECCV (1)
UAI (1)
Top co-authors
Research topics
Keywords
machine unlearning
(7)
adversarial training
(4)
large language model
(3)
transfer learning
(3)
model utility
(3)
bi-level optimization
(3)
model reprogramming
(2)
visual prompting
(2)
diffusion model
(2)
adversarial perturbation
(2)
neural network pruning
(2)
adversarial robustness
(2)
knowledge editing
(2)
min-max optimization
(2)
robust classification
(2)
network pruning
(2)
model editing
(2)
mixture of expert
(2)
lottery ticket hypothesis
(2)
neural network
(2)
Papers
Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
ACL 2026
Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
CVPR 2025
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
ICLR 2025
Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective
AAAI 2025
Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
EMNLP 2025
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
ICML 2025
Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design
ICCV 2025
SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
ACL 2025
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
ICML 2025
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
NIPS 2024
DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training
ICLR 2024
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
ICLR 2024
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
ICML 2024
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
NIPS 2024
To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
ECCV 2024
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
EMNLP 2024
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
NIPS 2024
Robust Mixture-of-Expert Training for Convolutional Neural Networks
ICCV 2023
Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
NIPS 2023
Understanding and Improving Visual Prompting: A Label-Mapping Perspective
CVPR 2023
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
ICLR 2023
What Is Missing in IRM Training and Evaluation? Challenges and Solutions
ICLR 2023
Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach
ICML 2023
Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization
ICML 2022
Advancing Model Pruning via Bi-level Optimization
NIPS 2022
Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free
CVPR 2022
Distributed adversarial training to robustify deep neural networks at scale
UAI 2022
Fairness Reprogramming
NIPS 2022