Y
Yisong Yue
Publications - 19
Citations - 89
Yisong Yue is an academic researcher. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 4, co-authored 19 publications receiving 89 citations.
Papers
More filters
Journal ArticleDOI
Neural-Fly enables rapid learning for agile flight in strong winds
Michael O'Connell,Guanya Shi,Xichen Shi,Kamyar Azizzadenesheli,Animashree Anandkumar,Yisong Yue,Soon-Jo Chung +6 more
TL;DR: This work presents Neural-Fly, a learning-based approach that allows rapid online adaptation by incorporating pretrained representations through deep learning and achieves precise flight control with substantially smaller tracking error than state-of-the-art nonlinear and adaptive controllers.
Proceedings Article
LyaNet: A Lyapunov Framework for Training Neural ODEs
TL;DR: Theoretically, it is shown that minimizing Lyapunov loss guarantees exponential convergence to the correct solution and enables a novel robustness guarantee, and empirically, LyaNet can offer improved prediction performance, faster convergence of inference dynamics, and improved adversarial robustness.
Journal ArticleDOI
MLNav: Learning to Safely Navigate on Martian Terrains
Shreyansh Daftry,Neil Abcouwer,Tyler del Sesto,Siddarth Venkatraman,Jialin Song,Lucas Igel,Amos Byon,Ugo Rosolia,Yisong Yue,Masahiro Ono +9 more
TL;DR: Compared to the baseline ENav path planner on board the Perserverance rover, MLNav can provide a significant improvement in multiple key metrics, such as a 10x reduction in collision checks when navigating real Martian terrains, despite being trained with synthetic terrains.
Journal ArticleDOI
Neurosymbolic Programming for Science
Jennifer J. Sun,Megan Tjandrasuwita,Atharva Sehgal,A. Solar-Lezama,Swarat Chaudhuri,Yisong Yue,Omar Costilla-Reyes +6 more
TL;DR: There are opportunities and challenges between current NP models and scientific workflows, with real-world examples from behavior analysis in science.
Proceedings ArticleDOI
Investigating Generalization by Controlling Normalized Margin
TL;DR: It is suggested that networks can be produced where normalized margin has seemingly no relationship with generalization, counter to the theory of Bartlett et al. (2017), and that yes — in a standard training setup, test performance closely tracks normalized margin.