[ NeurIPS 2023 ] Official Codebase for "Conformal Meta-learners for Predictive Inference of Individual Treatment Effects"

AAAI 22 - Training a Resilient Q-Network against Observational Interference, Causal Inference Q-Networks

Code for TEDVAE, a VAE-based treatment effect estimation algorithm.

Causal weights for macroeconomic shocks

The official code of "Adversarial Counterfactual Environment Model Learning" (NeurIPS'23 spotlight)

Implementation for the paper "Detecting critical treatment effect bias in small subgroups"

[ AISTATS 2026 ] Official Codebase for "Hybrid Meta-learners for Estimating Heterogeneous Treatment Effects"

Code for 'Estimating Treatment Effects with Independent Component Analysis' (arXiv:2507.16467)

Applying AI to medical use cases: Diagnoses of lung and brain disorders, Building risk models and survival estimators for heart disease via RF, and Using NLP to extract information from radiology reports.

Official code for "Resolving the bias-precision paradox in medical AI to reduce risks in decision support". GITO is a causal inference framework for treatment outcome prediction in critical care, featuring sampling-based MMD (sMMD) for distributional alignment, Integrated Gradients interpretability, and LLM-powered clinical narratives.

"Causal Machine Learning for Cost-Effective Allocation of Electricity Aid" thesis for my Masters in Management and Digital Technologies at Ludwig-Maximillian Univeristy, Munich.