Research archive · 2022—2024
Work spanning robustness, generative models, causal inference, and interpretability. My doctoral research at UCLA asked how we can build systems that learn the right things—and let us inspect why.
adversarial robustness · data poisoning
PureGen purifies poisoned training data using iterative Langevin dynamics of Energy-Based Models and Denoising Diffusion Probabilistic Models, achieving state-of-the-art poison defense with minimal impact on classifier generalization.
generative models · VAE
A composable latent space augmentation framework using VAEs that allows augmentations to be combined through linear transformations, preserving specific augmentation variances and improving geometric interpretability over standard and Conditional VAEs.
causal inference · hypothesis testing
CSHTEST and CSVHTEST use non-parametric structural causal knowledge and deep neural networks to perform hypothesis testing on causal models, validated on simulated DAGs, a synthetic pendulum dataset, and real-world medical trauma data.
fairness · debiasing
CCGM combines a causal latent space VAE with modifications for causal fidelity to generate de-biased datasets from biased training data, offering fine-grained control over causal structure in both image and tabular data generation.