Haowei Wang

A theoretically grounded EI algorithm for continuous simulation optimization achieves simple-regret guarantees by learning unknown heteroscedastic noise and optimizing incumbent/recommendation strategies based on regret bounds.

MSCNet not only reconstructs missing MRI sequences but also enhances lesion fidelity, outperforming traditional methods in clinical settings.

Clinician-interactive AI can boost diagnostic accuracy and consistency in thyroid ultrasound reporting while reducing time spent on segmentation and reporting tasks.

ForensicsTok achieves unprecedented precision in image tampering localization by directly generating spatially grounded token sequences, bypassing traditional bottlenecks.

Stop wasting compute: this work delivers a practical, provably optimal way to terminate Bayesian Optimization.