Zeyu Qin
8 papers · 2021–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI · Artificial Intelligence
(6)
Machine Learning
(5)
Learning Types · Machine Learning
(5)
Deep Learning
(3)
Natural Language Processing
(2)
Learning Types · Deep Learning
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Security & Privacy
(1)
Analysis
(1)
Applications
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Generation
(1)
Keywords
backdoor attack
(2)
backdoor defense
(2)
black-box attack
(2)
adversarial robustness
(2)
deep neural network
(2)
sequential decision making
(1)
gaussian noise
(1)
game theory
(1)
distribution shift
(1)
importance sampling
(1)
domain adaptation
(1)
gradient estimation
(1)
adversarial attack
(1)
entropy regularization
(1)
imitation learning
(1)
adversarial learning
(1)
adversarial perturbation
(1)
surrogate model
(1)
supervised fine-tuning
(1)
catastrophic forgetting
(1)
Papers
Preserving Diversity in Supervised Fine-Tuning of Large Language Models
ICLR 2025
Safety Reasoning with Guidelines
ICML 2025
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
NeurIPS 2024
Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators
EMNLP 2023
Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
NeurIPS 2023
Towards Stable Backdoor Purification through Feature Shift Tuning
NeurIPS 2023
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
NeurIPS 2022
Random Noise Defense Against Query-Based Black-Box Attacks
NeurIPS 2021