Mengxuan Hu
10 papers · 2024–2026 · 7 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (26) 🤝 Dynamic Duo (10) 💎 Century Club · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI
(8)
Machine Learning
(6)
Application Areas
(5)
Deep Learning
(4)
Learning Types · Machine Learning
(4)
Learning Types · Deep Learning
(2)
Optimization & Theory
(2)
Computer Vision
(1)
Knowledge & Reasoning
(1)
Natural Language Processing
(1)
Analysis
(1)
Models
(1)
Processing
(1)
Reasoning
(1)
Keywords
backdoor attack
(3)
large language model
(3)
causal inference
(3)
adversarial learning
(1)
causal reasoning
(1)
computer vision
(1)
domain generalization
(1)
source-free domain adaptation
(1)
interpretable machine learning
(1)
pseudo labeling
(1)
feature attribution
(1)
semantic alignment
(1)
model editing
(1)
computational efficiency
(1)
domain knowledge
(1)
class imbalance
(1)
causal discovery
(1)
adversarial attack
(1)
generative model
(1)
model security
(1)
Papers
Reducing Token Redundancy in LVLMs: A Systematic Review of Token Pruning Methods
ACL 2026
BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing
ICML 2025
Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
ICML 2025
Large Language Models for Causal Discovery: Current Landscape and Future Directions
IJCAI 2025
Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data
ICLR 2025
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
EMNLP 2025
Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety
CVPR 2025
UFID: A Unified Framework for Black-box Input-level Backdoor Detection on Diffusion Models
AAAI 2025
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract)
AAAI 2024
Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction
AAAI 2024