1 citations · 1 across the 2 of their papers we have counts for
3 papers · 1 filter
AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs
Mert Ünsal, Timon Gehr, Martin Vechev
We present the first correct-by-construction learning-based system for step-by-step mathematical integration. The key idea is to learn a policy, represented by a GPT transformer mo…
Provably Robust Adversarial Examples
Dimitar I. Dimitrov, Gagandeep Singh, Timon Gehr +1
We introduce the concept of provably robust adversarial examples for deep neural networks - connected input regions constructed from standard adversarial examples which are guarant…
Robustness Certification of Generative Models
Matthew Mirman, Timon Gehr, Martin Vechev
Generative neural networks can be used to specify continuous transformations between images via latent-space interpolation. However, certifying that all images captured by the resu…