3 papers
eess.SY2026
Learning Safe-by-Design Neural Network Controllers
Yang Zhao, Jungeun Lee, Jeong hwan Jeon +1
Safety filters constructed from control barrier functions (CBFs) are commonly appended to pre-trained neural network controllers to enforce safety requirements. However, this decou…
cs.LG2026
CAffNet: Hard Constraint-Affine Neural Networks
Yang Zhao, Jungeun Lee, Jeong hwan Jeon +1
We present a novel framework for embedding hard constraint satisfaction into neural network (NN) architectures, specifically feedforward neural networks and transformers, with inpu…
cs.LG2025
2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency
Yonggan Fu, Yang Zhao, Qixuan Yu +2
The recent breakthroughs of deep neural networks (DNNs) and the advent of billions of Internet of Things (IoT) devices have excited an explosive demand for intelligent IoT devices…