Ronghui Mu
10 papers · 2023–2026 · 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 ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (26) 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 🏆 Keyword Champion (2)
🗃️
Keyword Collector
(56)
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(6)
Core AI
(6)
Learning Types · Machine Learning
(6)
Deep Learning
(4)
Learning Types · Deep Learning
(4)
Application Areas
(3)
Optimization & Theory · Machine Learning
(3)
Reinforcement Learning
(2)
Methods
(2)
Optimization & Theory · Deep Learning
(1)
Techniques
(1)
Keywords
adversarial robustness
(5)
policy smoothing
(2)
large language model
(2)
spectral norm
(2)
confusion matrix
(2)
adversarial training
(2)
robust fairness
(2)
convex optimization
(1)
risk management
(1)
adversarial learning
(1)
class imbalance
(1)
spectral regularization
(1)
perturbation analysis
(1)
worst-case performance
(1)
ai safety
(1)
loss landscape
(1)
false discovery rate
(1)
adversarial attack
(1)
adversarial perturbation
(1)
distributional robustness
(1)
Papers
CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing
AAAI 2026
Confusion-Aware Spectral Regularizer for Long-Tailed Recognition
CVPR 2026
Enhancing Robust Fairness via Confusional Spectral Regularization
ICLR 2025
Safety of Embodied Navigation: A Survey
IJCAI 2025
Position: Building Guardrails for Large Language Models Requires Systematic Design
ICML 2024
PRASS: Probabilistic Risk-averse Robust Learning with Stochastic Search
IJCAI 2024
Reward Certification for Policy Smoothed Reinforcement Learning
AAAI 2024
Towards Fairness-Aware Adversarial Learning
CVPR 2024
Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning
AAAI 2023
Randomized Adversarial Training via Taylor Expansion
CVPR 2023