J. Edward Hu

2 accepted papers

2020

Guided Generation of Cause and Effect

Zhongyang Li, Xiao Ding, Ting Liu, J. Edward Hu, Benjamin Van Durme

IJCAI 2020poster

We present a conditional text generation framework that posits sentential expressions of possible causes and effects. This framework depends on two novel resources we develop in the course of this work: a very large-scale collection of English sentences expressing causal patterns (CausalBank); and a…

Cited by 0 Source ↗PDF ↗Scholar ↗

2020

Randomized Smoothing of All Shapes and Sizes

Greg Yang, Tony Duan, J. Edward Hu, Hadi Salman, Ilya Razenshteyn, Jerry Li

ICML 2020poster

Randomized smoothing is the current state-of-the-art defense with provable robustness against $\ell_2$ adversarial attacks. Many works have devised new randomized smoothing schemes for other metrics, such as $\ell_1$ or $\ell_\infty$; however, substantial effort was needed to derive such new guarant…

Cited by 242 Source ↗PDF ↗code ↗Scholar ↗