Developing theoretical foundations and practical algorithms for fair, interpretable, and causally-grounded machine learning systems.
We are an academic research organization dedicated to advancing the science of AI Fairness and Causal Machine Learning. Our work bridges theoretical foundations with practical implementations, ensuring AI systems are equitable, transparent, and grounded in causal understanding.
|
Fairness Metrics
|
Causal Discovery
|
Fair Treatment
|
Interpretability
|
| ⚖️ Fairness | 🔗 Causality | 🔍 Explainable AI |
|---|---|---|
| Algorithmic bias detection & mitigation | Causal discovery & inference | Interpretable ML models |
| Fair representation learning | Counterfactual reasoning | Transparent decision-making |
Alex RMIT VXLab |
Bowen RMIT Race |
Cyrus RMIT Race |
Patrick RMIT Race |
Thilina RMIT VXLab |
Ziqi RMIT |
Jing RMIT |
| ⚖️ Equity |
🔬 Rigor |
🌐 Openness |
🤝 Collaboration |
🎯 Impact |
| Fair AI for all | Scientific excellence | Open science | Community first | Real-world change |
Fair Intelligence • Advancing Trustworthy AI Through Fairness & Causality Research
🌟 Star our repositories to support open research in AI fairness! 🌟
