Machine-learned wearable sensors for real-time hand-motion recognition: toward practical applications

KR Pyun, K Kwon, MJ Yoo, KK Kim… - National science …, 2024 - academic.oup.com
Soft electromechanical sensors have led to a new paradigm of electronic devices for novel
motion-based wearable applications in our daily lives. However, the vast amount of random …

Barriernet: Differentiable control barrier functions for learning of safe robot control

W Xiao, TH Wang, R Hasani, M Chahine… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Many safety-critical applications of neural networks, such as robotic control, require safety
guarantees. This article introduces a method for ensuring the safety of learned models for …

Simulation intelligence: Towards a new generation of scientific methods

A Lavin, D Krakauer, H Zenil, J Gottschlich… - arXiv preprint arXiv …, 2021 - arxiv.org
The original" Seven Motifs" set forth a roadmap of essential methods for the field of scientific
computing, where a motif is an algorithmic method that captures a pattern of computation …

Layout-based causal inference for object navigation

S Zhang, X Song, W Li, Y Bai, X Yu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Previous works for ObjectNav task attempt to learn the association (eg relation graph)
between the visual inputs and the goal during training. Such association contains the prior …

Liquid structural state-space models

R Hasani, M Lechner, TH Wang, M Chahine… - arXiv preprint arXiv …, 2022 - arxiv.org
A proper parametrization of state transition matrices of linear state-space models (SSMs)
followed by standard nonlinearities enables them to efficiently learn representations from …

Robust flight navigation out of distribution with liquid neural networks

M Chahine, R Hasani, P Kao, A Ray, R Shubert… - Science Robotics, 2023 - science.org
Autonomous robots can learn to perform visual navigation tasks from offline human
demonstrations and generalize well to online and unseen scenarios within the same …

Closed-form continuous-time neural networks

R Hasani, M Lechner, A Amini, L Liebenwein… - Nature Machine …, 2022 - nature.com
Continuous-time neural networks are a class of machine learning systems that can tackle
representation learning on spatiotemporal decision-making tasks. These models are …

Brain-inspired computing: A systematic survey and future trends

G Li, L Deng, H Tang, G Pan, Y Tian… - Proceedings of the …, 2024 - ieeexplore.ieee.org
Brain-inspired computing (BIC) is an emerging research field that aims to build fundamental
theories, models, hardware architectures, and application systems toward more general …

Social ode: Multi-agent trajectory forecasting with neural ordinary differential equations

S Wen, H Wang, D Metaxas - European Conference on Computer Vision, 2022 - Springer
Multi-agent trajectory forecasting has recently attracted a lot of attention due to its
widespread applications including autonomous driving. Most previous methods use RNNs …

Care: Modeling interacting dynamics under temporal environmental variation

X Luo, H Wang, Z Huang, H Jiang… - Advances in …, 2024 - proceedings.neurips.cc
Modeling interacting dynamical systems, such as fluid dynamics and intermolecular
interactions, is a fundamental research problem for understanding and simulating complex …