Haiqin Weng
4 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 · Silver
🗺️
Taxonomy Completionist
(11)
Top co-authors
Research topics
Artificial Intelligence
(4)
Core AI
(3)
Computer Science
(1)
Computer Vision
(1)
Deep Learning
(1)
Machine Learning
(1)
Natural Language Processing
(1)
Analysis
(1)
Applications · Natural Language Processing
(1)
Applications · Computer Science
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Processing
(1)
Keywords
large language model
(2)
neural network
(2)
image forgery detection
(1)
harmful content
(1)
safety alignment
(1)
saliency map
(1)
noise analysis
(1)
synthetic data
(1)
counterfactual explanation
(1)
jailbreak attack
(1)
information leakage
(1)
safety benchmark
(1)
deep inpainting
(1)
image forensics
(1)
universal detection
(1)
noise pattern
(1)
output evaluation
(1)
causal inference
(1)
semantic sensitive information
(1)
preference learning
(1)
Papers
A Benchmark for Semantic Sensitive Information in LLMs Outputs
ICLR 2025
Course-Correction: Safety Alignment Using Synthetic Preferences
EMNLP 2024
Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks
ICCV 2023
Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting
IJCAI 2021