Robot Model Identification and Learning: A Modern Perspective

T Lee, J Kwon, PM Wensing… - Annual Review of Control …, 2023 - annualreviews.org
In recent years, the increasing complexity and safety-critical nature of robotic tasks have
highlighted the importance of accurate and reliable robot models. This trend has led to a …

Towards understanding generalization of graph neural networks

H Tang, Y Liu - International Conference on Machine …, 2023 - proceedings.mlr.press
Graph neural networks (GNNs) are widely used in machine learning for graph-structured
data. Even though GNNs have achieved remarkable success in real-world applications …

Physics-aware machine learning revolutionizes scientific paradigm for machine learning and process-based hydrology

Q Xu, Y Shi, J Bamber, Y Tuo, R Ludwig… - arxiv preprint arxiv …, 2023 - arxiv.org
Accurate hydrological understanding and water cycle prediction are crucial for addressing
scientific and societal challenges associated with the management of water resources …

Equivariant spatio-temporal attentive graph networks to simulate physical dynamics

L Wu, Z Hou, J Yuan, Y Rong… - Advances in Neural …, 2024 - proceedings.neurips.cc
Learning to represent and simulate the dynamics of physical systems is a crucial yet
challenging task. Existing equivariant Graph Neural Network (GNN) based methods have …

Latent field discovery in interacting dynamical systems with neural fields

MM Kofinas, E Bekkers, N Nagaraja… - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract Systems of interacting objects often evolve under the influence of underlying field
effects that govern their dynamics, yet previous works have abstracted away from such …

Unifying predictions of deterministic and stochastic physics in mesh-reduced space with sequential flow generative model

L Sun, X Han, H Gao, JX Wang… - Advances in Neural …, 2024 - proceedings.neurips.cc
Accurate prediction of dynamical systems in unstructured meshes has recently shown
successes in scientific simulations. Many dynamical systems have a nonnegligible level of …

Geometry-complete perceptron networks for 3d molecular graphs

A Morehead, J Cheng - Bioinformatics, 2024 - academic.oup.com
Motivation The field of geometric deep learning has recently had a profound impact on
several scientific domains such as protein structure prediction and design, leading to …

Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems

Q Hernández, A Badías, F Chinesta, E Cueto - Computational Mechanics, 2023 - Springer
We develop inductive biases for the machine learning of complex physical systems based
on the port-Hamiltonian formalism. To satisfy by construction the principles of …

Equivariant graph neural operator for modeling 3d dynamics

M Xu, J Han, A Lou, J Kossaifi, A Ramanathan… - arxiv preprint arxiv …, 2024 - arxiv.org
Modeling the complex three-dimensional (3D) dynamics of relational systems is an
important problem in the natural sciences, with applications ranging from molecular …

Subequivariant graph reinforcement learning in 3D environments

R Chen, J Han, F Sun, W Huang - … Conference on Machine …, 2023 - proceedings.mlr.press
Learning a shared policy that guides the locomotion of different agents is of core interest in
Reinforcement Learning (RL), which leads to the study of morphology-agnostic RL …