Jason Wang
5 papers · 2022–2026 · 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 · Silver
🗺️
Taxonomy Completionist
(14)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Machine Learning
(4)
Natural Language Processing
(3)
Artificial Intelligence
(2)
Deep Learning
(2)
Application Areas
(2)
Core AI
(2)
Resources & Methods
(2)
Security & Privacy
(1)
Applications
(1)
Architectures
(1)
Core Methods
(1)
Learning Types
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Privacy
(1)
Keywords
large language model
(2)
transformer architecture
(1)
learning theory
(1)
privacy attack
(1)
text classification
(1)
graph learning
(1)
self-supervised learning
(1)
offensive language detection
(1)
humor detection
(1)
statistical query
(1)
hessian matrix
(1)
complexity bound
(1)
compositional representation
(1)
manifold hypothesis
(1)
hardness result
(1)
membership inference attack
(1)
character embedding
(1)
privacy evaluation
(1)
benchmark construction
(1)
parameter perturbation
(1)
Papers
CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models
ACL 2026
Hardness of Learning Neural Networks under the Manifold Hypothesis
NeurIPS 2024
MoPe: Model Perturbation based Privacy Attacks on Language Models
EMNLP 2023
The Naughtyformer: A Transformer Understands and Moderates Adult Humor (Student Abstract)
AAAI 2023
Augmentation of Chinese Character Representations with Compositional Graph Learning (Student Abstract)
AAAI 2022