Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments

no code implementations • 22 Feb 2023 • Jason Xinyu Liu, ZiYi Yang, Ifrah Idrees, Sam Liang, Benjamin Schornstein, Stefanie Tellex, Ankit Shah

We propose Lang2LTL, a modular system and a software package that leverages large language models (LLMs) to ground temporal navigational commands to LTL specifications in environments without prior language data.

Minority Reports Defense: Defending Against Adversarial Patches

no code implementations • 28 Apr 2020 • Michael McCoyd, Won Park, Steven Chen, Neil Shah, Ryan Roggenkemper, Minjune Hwang, Jason Xinyu Liu, David Wagner

We propose a defense against patch attacks based on partially occluding the image around each candidate patch location, so that a few occlusions each completely hide the patch.

Adversarial Attack General Classification +1