Research
Research
Questions I've worked on — from uncertainty under distribution shift to what it takes to train and evaluate time-series foundation models.
- M.Tech Thesis · IIT Bombay2024
Uncertainty Modelling for Open Domain Generalization
Open domain generalization requires a model to perform on domains unseen during training, where both the input distribution and the label space may differ. This thesis studies how predictive uncertainty should be modeled and used in that setting — so a model can express calibrated doubt about the inputs and classes it was never trained on, and defer rather than fail silently.
- ICASSP 2026 · CODS 20262026
Data-Centric Pretraining for Time-Series Foundation Models
A line of work on the data behind time-series foundation models: how to measure what a pretraining corpus actually contributes, select the samples that matter, and synthesize new data to close specific coverage gaps — improving forecasting while shrinking the corpus.
Publications & Patents
- Published
Time Series Attributes Guided Pretraining Data Selection for Time Series Foundation Models
ICASSP · 2026
- Under review
Close the Gap: Targeted Synthetic Data to Augment the Pretraining Corpus of Time Series Foundation Models
CODS · 2026
- Published
Using Time Series Foundation Models for Atmospheric CO₂ Concentration Forecasting
NeurIPS — Climate Change AI (CCAI) Workshop · 2025
- Published
Advancing Flood Mapping with Geo-Spatial Foundation Models and Indian Satellites
IGARSS · 2025
- Filed
Estimating Greenhouse Gas Emissions Using Satellite Data and Machine Learning
US Patent · 2024