Abstract: The construction of control barrier functions (CBFs) based on differentiable optimization ensures the invariance of dynamic systems, which is suitable for collision-free motion planning of ...
Abstract: Training deep neural networks on unaligned sequence data is fundamental to tasks such as automatic speech recognition, lyrics alignment, and automatic music transcription (AMT). Popular loss ...
We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training. Despite the recent progress, existing methods mainly ...
Economists have developed different types of models describing the interaction of agents in markets. Early models in general equilibrium theory describe agents taking prices as given and do not ...
The success of a molecular dynamics simulation depends on the accuracy of the force field used to define the atomic interactions. It is challenging to train both classical and modern machine-learning ...
We thank Petr Sulc, Tom Ouldridge, Jonathan Doye, Lorenzo Rovigatti, Erik Poppleton, and Ard Louis for support and helpful discussions surrounding the oxDNA force field and the oxDNA ecosystem. We ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results