Xiaowei Jia

Black-box GNN APIs can be stolen with 18% higher fidelity using an order of magnitude fewer queries, shattering the assumption that hard-label rate limits protect proprietary graph architectures.

Treating natural state trajectories as self-supervised "actions" turns static scientific emulators into interactive, counterfactual world models without requiring manually labeled intervention data.

EventTime outperforms traditional forecasting models by effectively quantifying the financial impact of cybersecurity breaches, revealing a new frontier in event-driven market analysis.

PIER outperforms standard retrieval methods by ensuring that environmental predictions are consistent with physical dynamics, leading to more accurate modeling of complex systems.