Jane C. Odum — PhD Student in Computer Science

Open to Collaborate

NES Lab (Neuro-Symbolic Computing Lab), University of Georgia — under Dr. John Miller

Athens, Georgia

PhD Student, 2021–Present

Research Focus

Generative AI & Forecasting

Advancing time series prediction through generative models

Time Series Forecasting

Diffusion Models

Generative AI

Interpretability

Experience

ML Engineer Intern

Stripe • Summer 2025

ML models for fraud detection, Spark/Databricks pipelines at scale

Research Output

Projects completed

ML, AI & Software

Education

2021

PhD in Computer Science

University of Georgia

Expected May 2026 • Generative AI & Time Series

Tools & Software

Python PyTorch TensorFlow C/C++ Java Spark LLMs NLP Deep Learning

Always exploring new tools

Current Position

I am a Computer Science Ph.D. candidate (expected May 2026) in the NES Lab (Neuro-Symbolic Computing Lab) at University of Georgia, working under Dr. John Miller. My research focuses on advancing time series forecasting through generative models, machine learning, and deep learning techniques.

In Summer 2025, I interned as a Machine Learning Engineer at Stripe, where I developed and deployed ML models for secret key leak detection — cutting detection latency from 4.5 days to under 1 hour and engineering large-scale feature pipelines in Spark/Databricks processing 500M+ records.

What I Do

I develop machine learning systems that predict future trends from complex time series data. My work involves designing and training generative models, such as diffusion models, to address real-world challenges like noisy data, uncertainty, and shifting patterns. I am also interested in interpretability in diffusion models. I am particularly interested in applications where precise forecasts can drive meaningful impact, whether in predicting disease spread during pandemics or anticipating economic and social trends. My goal is to create models that are both powerful and practical, that drives better decision-making.

My recent publication, Adaptive Quantile Guidance in Diffusion Models (ICMLA 2025, Accepted), achieved 73.3% lower MAE than state-of-the-art models across pandemic forecasting scenarios.

My Background

Before my Ph.D., I earned a Bachelor’s degree in Computer Science from the University of Ilorin, Nigeria, where I developed a passion for solving problems through code. I later honed my software engineering skills at the 42 Silicon Valley bootcamp in California, gaining experience in building scalable systems and collaborating on complex technical projects.

Now, as a researcher, I blend my engineering mindset with my passion for machine learning. My current work focuses on using generative models and deep learning to advance time series forecasting, especially in high-stakes areas like pandemic prediction. Solving challenges such as sparse data and continuous updates, I aim to create AI tools that are both robust and easily accessible to the communities that need them most.

When I am not immersed in research or coding, I love staying active with weight lifting and hiking, getting creative through painting and dancing, and experimenting in the kitchen with new recipes.

Selected Publications

2025

AQDiff

Adaptive Quantile Guidance in Diffusion Models: Multi-Dataset Learning for Pandemic Time Series (Accepted to ICMLA 2025)

J. Odum^*† , and J. Miller^*

. More Information can be found here , 2025

Abs PDF

Probabilistic forecasting of epidemiological time series remains challenging due to non-stationary disease dynamics, sparse observations, and heterogeneous data regimes. We present Adaptive Quantile Diffusion (AQDiff), a novel diffusion-based framework that addresses these challenges through two key innovations: (1) multi-dataset pre-training of a unified time series diffusion model across heterogeneous epidemiological domains, and (2) adaptive quantile guidance that dynamically adjusts prediction intervals based on local residual statistics. AQDiff introduces a feedback loop where recent forecast errors inform quantile adjustments through an exponentially weighted buffer, enabling real-time adaptation to volatility shifts. Pre-training on influenza-like illness (ILI), COVID-19, and respiratory syncytial virus (RSV) data from the U.S. Centers for Disease Control and Prevention (CDC) allows cross-domain knowledge transfer. Experiments demonstrate that AQDiff reduces mean absolute error (MAE) by as much as 73.3% compared to state-of-the-art baselines (CSDI, PatchTST) across three pandemic forecasting tasks. Our analysis reveals that adaptive quantile guidance provides statistically significant improvements during outbreak surges, while pre-training enhances robustness to limited training data. The framework maintains computational efficiency, adding less than 10% overhead compared to fixed-quantile diffusion models.