Deep Learning
PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations
·5378 words·26 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Machine Learning
Deep Learning
🏢 Department of Artificial Intelligence, Sungkyunkwan University
Physics-Informed Gaussians (PIGs) revolutionize PDE solving by using adaptive, learnable Gaussian functions for superior accuracy and efficiency.
Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
·3440 words·17 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Machine Learning
Deep Learning
🏢 Google Research
Hybrid Graph Sequence Model (GSM++) outperforms existing models by using hierarchical sequences and a hybrid architecture of Transformers and recurrent models, effectively capturing both local and glo…
Improving the detection of technical debt in Java source code with an enriched dataset
·1778 words·9 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Machine Learning
Deep Learning
🏢 Hanoi University of Science and Technology
Enriched dataset TESORO improves technical debt detection by combining self-admitted comments and Java source code, advancing state-of-the-art models.
SambaMixer: State of Health Prediction of Li-ion Batteries using Mamba State Space Models
·3912 words·19 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Machine Learning
Deep Learning
🏢 UNED - Universidad Nacional De Educación a Distancia, Madrid, Spain
SambaMixer: A novel state-space model accurately predicts Li-ion battery health using efficient Mamba architecture and innovative resampling techniques.