no code implementations • 2 May 2024 • Zhenjiang Mao, Dong-You Jhong, Ao Wang, Ivan Ruchkin
With the rise of large foundation models, multimodal inputs offer the possibility of taking human language as a latent representation, thus enabling language-defined OOD detection.
no code implementations • 30 Mar 2024 • Zhenjiang Mao, Siqi Dai, Yuang Geng, Ivan Ruchkin
A world model creates a surrogate world to train a controller and predict safety violations by learning the internal dynamic model of systems.
1 code implementation • 8 Nov 2023 • Yuang Geng, Jake Brandon Baldauf, Souradeep Dutta, Chao Huang, Ivan Ruchkin
Autonomous systems are increasingly implemented using end-to-end learning-based controllers.
1 code implementation • 6 Nov 2023 • Pengyuan Lu, Matthew Cleaveland, Oleg Sokolsky, Insup Lee, Ivan Ruchkin
However, existing repair techniques do not preserve previously correct behaviors.
no code implementations • 1 Sep 2023 • Sydney Pugh, Ivan Ruchkin, Insup Lee, James Weimer
However, ensuring the robustness of these models is vital for building trustworthy AI systems.
no code implementations • 28 Aug 2023 • Souradeep Dutta, Michele Caprio, Vivian Lin, Matthew Cleaveland, Kuk Jin Jang, Ivan Ruchkin, Oleg Sokolsky, Insup Lee
A particularly challenging problem in AI safety is providing guarantees on the behavior of high-dimensional autonomous systems.
1 code implementation • 23 Aug 2023 • Zhenjiang Mao, Carson Sobolewski, Ivan Ruchkin
End-to-end learning has emerged as a major paradigm for developing autonomous systems.
no code implementations • 6 Apr 2023 • Pengyuan Lu, Ivan Ruchkin, Matthew Cleaveland, Oleg Sokolsky, Insup Lee
However, given the high diversity and complexity of LECs, it is challenging to encode domain knowledge (e. g., the CPS dynamics) in a scalable actual causality model that could generate useful repair suggestions.
1 code implementation • 3 Nov 2021 • Ivan Ruchkin, Matthew Cleaveland, Radoslav Ivanov, Pengyuan Lu, Taylor Carpenter, Oleg Sokolsky, Insup Lee
To predict safety violations in a verified system, we propose a three-step confidence composition (CoCo) framework for monitoring verification assumptions.