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 • 23 Aug 2023 • Zhenjiang Mao, Carson Sobolewski, Ivan Ruchkin
End-to-end learning has emerged as a major paradigm for developing autonomous systems.