Flora D. Salim

AsyTO achieves state-of-the-art forecasting accuracy while keeping model complexity linear, challenging the notion that more parameters always lead to better performance.

A2TTA transforms the challenge of evolving traffic networks into a robust adaptation strategy, significantly enhancing forecasting accuracy in dynamic environments.

Scope3Trace achieves high accuracy in extracting Scope 3 emissions data while providing transparent evidence grounding, revolutionizing how we analyze corporate carbon footprints.

TopoBrick achieves superior zero-shot forecasting by intelligently sampling exogenous variables based on building topology, outperforming traditional models without the need for extensive training.

Sparse rewards are transformed into dense supervision, enabling VLA models to adapt robustly in real-time across diverse robotic tasks.

NLICV not only speeds up LLM personalization evaluation by up to 2100 times but also offers a clearer understanding of model behaviors beyond simple binary scoring.

Income and education drive self-reporting rates of illness more than geography or messaging, revealing critical insights for public health strategies.