Yilin Zhang

Calibration-Aware Uncertainty Cascades is proposed, a simple post-hoc framework that independently calibrates each model's confidence and selects deployment policies using validation data and shows theoretically that calibration gives confidence thresholds an explicit selective-risk interpretation, whereas uncalibrated scores offer no comparable reliability guarantee.

NICWhisper reveals that electromagnetic emissions from network interface cards can effectively identify network threats, achieving over 80% accuracy without analyzing packet data.

Token-oriented inference optimizations can cut production costs and boost efficiency, transforming large model services from merely callable to fully operable.

KeepLoRA++ reveals that effective continual learning hinges on strategically managing knowledge across different layers of a model, leading to significant performance gains in complex tasks.

Transition-based modeling reveals a more data-efficient approach to predicting Alzheimer's disease progression, outperforming traditional sequence models in accuracy.

Generate plausible follow-up spine DXA images by intervening on age, opening the door to simulating long-term skeletal changes.