Zeming Wei
7 papers · 2023–2025 · 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 · Bronze
🗺️
Taxonomy Completionist
(22)
Venues
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(6)
Learning Types · Machine Learning
(6)
Architectures
(4)
Learning Types · Deep Learning
(4)
Artificial Intelligence
(3)
Natural Language Processing
(3)
Core AI
(3)
Resources & Methods
(3)
Optimization & Theory · Deep Learning
(2)
Application Areas
(1)
Learning Paradigms
(1)
Optimization & Theory · Machine Learning
(1)
Techniques
(1)
Keywords
adversarial training
(4)
adversarial robustness
(3)
large language model
(3)
self-supervised learning
(1)
in-context learning
(1)
robust classification
(1)
model safety
(1)
sharpness-aware minimization
(1)
model editing
(1)
loss landscape
(1)
safety alignment
(1)
inductive bia
(1)
node classification
(1)
representation engineering
(1)
jailbreaking attack
(1)
weight averaging
(1)
robust overfitting
(1)
prompt optimization
(1)
softmax attention
(1)
multi-head attention
(1)
Papers
Identifying and Understanding Cross-Class Features in Adversarial Training
ICML 2025
Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models
NeurIPS 2024
A Theoretical Understanding of Self-Correction through In-context Alignment
NeurIPS 2024
Fight Back Against Jailbreaking via Prompt Adversarial Tuning
NeurIPS 2024
On the Duality Between Sharpness-Aware Minimization and Adversarial Training
ICML 2024
Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning
NeurIPS 2023
CFA: Class-Wise Calibrated Fair Adversarial Training
CVPR 2023