Zhengxiao Liu
5 papers · 2022–2025 · 3 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 · Silver
🗺️
Taxonomy Completionist
(25)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Machine Learning
(5)
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI
(4)
Learning Types · Machine Learning
(3)
Natural Language Processing
(2)
Application Areas
(2)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Optimization & Theory · Machine Learning
(2)
Optimization & Theory · Deep Learning
(2)
Resources & Methods
(2)
Computer Science
(1)
Data Science & Analytics
(1)
Applications
(1)
Keywords
pre-trained language model
(3)
backdoor attack
(2)
model compression
(2)
multi-task learning
(1)
maximum entropy
(1)
knowledge editing
(1)
parameter efficient
(1)
adversarial defense
(1)
language model
(1)
parameter-efficient tuning
(1)
neighborhood aggregation
(1)
parameter efficiency
(1)
inference acceleration
(1)
recommender system
(1)
factual association
(1)
gradient manipulation
(1)
early exiting
(1)
large language model
(1)
transformer model
(1)
graph neural network
(1)
Papers
Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models
AAAI 2025
Trust-GRS: A Trustworthy Training Framework for Graph Neural Network Based Recommender Systems Against Shilling Attacks
AAAI 2025
A Gradient Control Method for Backdoor Attacks on Parameter-Efficient Tuning
ACL 2023
Maximum Entropy Loss, the Silver Bullet Targeting Backdoor Attacks in Pre-trained Language Models
ACL 2023
COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models
EMNLP 2022