Mengnan Zhao
5 papers · 2018–2026 · 5 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 · Silver
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(19)
Top co-authors
Research topics
Machine Learning
(4)
Artificial Intelligence
(2)
Deep Learning
(2)
Natural Language Processing
(2)
Core AI
(2)
Learning Types
(2)
Optimization & Theory
(2)
Computer Science
(1)
Healthcare & Medicine
(1)
Application Areas
(1)
Applications · Natural Language Processing
(1)
Applications · Computer Science
(1)
Architectures
(1)
Core Methods
(1)
Generation
(1)
Keywords
catastrophic overfitting
(2)
adversarial training
(2)
question answering
(1)
prompt engineering
(1)
named entity recognition
(1)
neural network optimization
(1)
adaptive sampling
(1)
computational efficiency
(1)
text retrieval
(1)
spurious correlation
(1)
retrieval-augmented generation
(1)
multi-hop reasoning
(1)
long context
(1)
word embedding
(1)
negative sampling
(1)
long-context understanding
(1)
knowledge retrieval
(1)
extrinsic evaluation
(1)
intrinsic evaluation
(1)
softmax classifier
(1)
Papers
Mitigating Error Amplification in Fast Adversarial Training
CVPR 2026
Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts
EMNLP 2025
Fast Adversarial Training with Smooth Convergence
ICCV 2023
A Tale of Two Efficient and Informative Negative Sampling Distributions
ICML 2021
A Framework for Developing and Evaluating Word Embeddings of Drug-named Entity
ACL 2018