research
∙
09/21/2023
Parallelizing non-linear sequential models over the sequence length
Sequential models, such as Recurrent Neural Networks and Neural Ordinary...
share
research
∙
08/22/2022
Constants of motion network
The beauty of physics is that there is usually a conserved quantity in a...
research
∙
08/03/2022
Unifying physical systems' inductive biases in neural ODE using dynamics constraints
Conservation of energy is at the core of many physical phenomena and dyn...
research
∙
11/15/2021
Reducing the Long Tail Losses in Scientific Emulations with Active Learning
Deep-learning-based models are increasingly used to emulate scientific s...
research
∙
11/09/2020
Derivatives of partial eigendecomposition of a real symmetric matrix for degenerate cases
This paper presents the forward and backward derivatives of partial eige...
research
∙
12/22/2019