Results 101 to 110 of about 7,952,537 (299)

Review on Application of Spatial-Temporal Graph Neural Network in PM2.5 ConcentrationForecasting [PDF]

open access: yesJisuanji kexue
Atmospheric fine particulate matter(PM2.5) has garnered significant public attention due to its detrimental effects on health and the environment.Achieving high-precision spatial-temporal forecasting of PM2.5 concentrations is crucial for guiding ...
TANG Boyuan, LI Qi
doaj   +1 more source

Grounding Large Language Models for Robot Task Planning Using Closed‐Loop State Feedback

open access: yesAdvanced Robotics Research, EarlyView.
BrainBody‐Large Language Model (LLM) introduces a hierarchical, feedback‐driven planning framework where two LLMs coordinate high‐level reasoning and low‐level control for robotic tasks. By grounding decisions in real‐time state feedback, it reduces hallucinations and improves task reliability.
Vineet Bhat   +4 more
wiley   +1 more source

Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks

open access: yesProceedings of the 34th ACM International Conference on Information and Knowledge Management
Graph Neural Networks (GNNs) have emerged as the leading paradigm for learning over graph-structured data. However, their performance is limited by issues inherent to graph topology, most notably oversquashing and oversmoothing. Recent advances in graph rewiring aim to mitigate these limitations by modifying the graph topology to promote more effective
Hugo Attali   +3 more
openaire   +2 more sources

Evolving graph attention networks for dynamic link prediction.

open access: yesPLoS ONE
Graph neural networks (GNNs), which learn node representations via aggregating their neighbors, have shown superior performance and become the de facto efficient toolkit for analyzing and learning from data with structured properties.
Yucai Jiang   +6 more
doaj   +1 more source

Asymmetry in Skipping Enhances Viability Against Control Input Noise

open access: yesAdvanced Robotics Research, EarlyView.
Quadruped animals use asymmetric galloping gaits at high speeds, yet the functional role of this asymmetry remains unclear. This study shows that left–right asymmetry in touchdown angles enhances robustness to control noise. Using a simple two‐legged locomotion model and viability theory, it demonstrates that asymmetric skipping substantially enlarges ...
Yuichi Ambe, Alvin So, Shinya Aoi
wiley   +1 more source

Dynamic Spiking Framework for Graph Neural Networks [PDF]

open access: yes
The integration of Spiking Neural Networks (SNNs) and Graph Neural Networks (GNNs) is gradually attracting attention due to the low power consumption and high efficiency in processing the non-Euclidean data represented by graphs.
Xiong, Huan   +5 more
core   +1 more source

Tumbling Magnetic Microrobots for Targeted In Vivo Drug Delivery in the GI Tract

open access: yesAdvanced Robotics Research, EarlyView.
We introduce a microrobot design and integrated system for on‐demand targeted drug release in the gastrointestinal tract. The microrobot has an embedded magnet for actuation with external magnetic fields and is visualized in real time using ultrasound. It has two drug release ports sealed with a thermally sensitive wax. Local heating of the wax using a
Aaron C. Davis   +7 more
wiley   +1 more source

Auditory–Tactile Congruence for Synthesis of Adaptive Pain Expressions in RoboPatients

open access: yesAdvanced Robotics Research, EarlyView.
In this work, we explore auditory–tactile congruence for synthesizing adaptive vocal pain expressions in robopatients. Using a robopatient platform that integrates vocal pain sounds with palpation forces, we conducted 7680 trials across 20 participants.
Saitarun Nadipineni   +4 more
wiley   +1 more source

A Comparison between Recursive Neural Networks and Graph Neural Networks

open access: yes, 2006
Recursive neural networks (RNNs) and graph neural networks (GNNs) are two connectionist models that can directly process graphs. RNNs and GNNs exploit a similar processing framework, but they can be applied to different input domains.
V. Di Massa   +17 more
core   +1 more source

HALO-GNN: hallucination-resistant temporal graph neural networks for dynamic community detection

open access: yesScientific Reports
Temporal graph learning is inherently subject to illusory structural dynamics, which is a phenomenon in which transient noise and ephemeral perturbations are exaggerated into deceptive community movements.
Yanfei Ma, Daozheng Qu, Yibo Wang
doaj   +1 more source

Home - About - Disclaimer - Privacy