Recent papers by the TEA lab members (underlined):
- Zhenjiang Mao, Siqi Dai, Yuang Geng, Ivan Ruchkin. Zero-shot Safety Prediction for Autonomous Robots with Foundation World Models [Arxiv].
Preprint, in submission. - Yuang Geng, Souradeep Dutta, Ivan Ruchkin.
Bridging Dimensions: Confident Reachability for High-Dimensional Controllers [Arxiv].
Preprint, in submission. - Zhenjiang Mao, Carson Sobolewski, Ivan Ruchkin.
How Safe Am I Given What I See? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy [Arxiv] [Poster].
In Proceedings of the Annual Learning for Dynamics & Control Conference (L4DC), Oxford, UK, 2024. - Souradeep Dutta, Michele Caprio, Vivian Lin, Matthew Cleaveland, Kuk Jin Jang, Ivan Ruchkin, Oleg Sokolsky, Insup Lee.
Distributionally Robust Statistical Verification with Imprecise Neural Networks [Arxiv].
Preprint, in submission. - Pengyuan Lu, Matthew Cleaveland, Oleg Sokolsky, Insup Lee, Ivan Ruchkin.
Repairing Learning-Enabled Controllers While Preserving What Works [Arxiv] [Github].
In Proceedings of the International Conference on Cyber-Physical Systems (ICCPS), Hong Kong, China, 2024. - Sydney Pugh, Ivan Ruchkin, Insup Lee, James Weimer.
Curating Naturally Adversarial Datasets for Trustworthy AI in Healthcare [Arxiv] [Github].
In Proceedings of the International Conference on Cyber-Physical Systems (ICCPS), Hong Kong, China, 2024. - Matthew Cleaveland, Oleg Sokolsky, Insup Lee, Ivan Ruchkin.
Conservative Safety Monitors of Stochastic Dynamical Systems [ArXiv] [Springer] [Poster] [Slides].
In Proceedings of the NASA Formal Methods Symposium (NFM), Houston, TX, 2023. - Pengyuan Lu, Ivan Ruchkin, Matthew Cleaveland, Oleg Sokolsky, Insup Lee.
Causal Repair of Learning-Enabled Cyber-Physical Systems [ArXiv] [IEEE] [Slides] [Github].
In Proceedings of the International Conference on Assured Autonomy (ICAA), Baltimore, MD, 2023. - Ivan Ruchkin, Matthew Cleaveland, Radoslav Ivanov, Pengyuan Lu, Taylor Carpenter, Oleg Sokolsky, Insup Lee.
Confidence Composition for Monitors of Verification Assumptions [ArXiv] [IEEE] [Slides] [Talk].
In Proceedings of the International Conference on Cyber-Physical Systems (ICCPS), Milan, Italy, 2022.