A novel teacher-student ensemble of physics-informed deep learning models improves traffic state estimation under varying speed limit conditions by using a classifier to select appropriate physics-constrained models.
Deep learning
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A rectified flow model trained on 30 actuation-space demonstrations produces control sequences that yield 97.5% grasp success across the workspace, with generalization to object size changes of ±33% and execution speed scaling from 20% to 200%.
The paper surveys AI-driven collaborative spectrum sensing methods categorized by learning paradigms and positions semantic communication as a joint communication-computation framework for improved efficiency.
DualOpt decouples optimization by using real-time layer-wise weight decay for scratch training and weight rollback for fine-tuning to improve convergence, generalization, and reduce knowledge forgetting.
A ResNet50 OOD filter plus YOLOv8/11/12 pipeline reaches 99.77% OOD rejection accuracy and 0.947 mAP on mammograms while blocking irrelevant imaging inputs.
citing papers explorer
-
Physics-Informed Teacher-Student Ensemble Learning for Traffic State Estimation with a Varying Speed Limit Scenario
A novel teacher-student ensemble of physics-informed deep learning models improves traffic state estimation under varying speed limit conditions by using a classifier to select appropriate physics-constrained models.
-
Lightweight Learning from Actuation-Space Demonstrations via Flow Matching for Whole-Body Soft Robotic Grasping
A rectified flow model trained on 30 actuation-space demonstrations produces control sequences that yield 97.5% grasp success across the workspace, with generalization to object size changes of ±33% and execution speed scaling from 20% to 200%.
-
Collaborative Spectrum Sensing in Cognitive and Intelligent Wireless Networks: An Artificial Intelligence Perspective
The paper surveys AI-driven collaborative spectrum sensing methods categorized by learning paradigms and positions semantic communication as a joint communication-computation framework for improved efficiency.
-
Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning
DualOpt decouples optimization by using real-time layer-wise weight decay for scratch training and weight rollback for fine-tuning to improve convergence, generalization, and reduce knowledge forgetting.
-
Analysis of Invasive Breast Cancer in Mammograms Using YOLO, Explainability, and Domain Adaptation
A ResNet50 OOD filter plus YOLOv8/11/12 pipeline reaches 99.77% OOD rejection accuracy and 0.947 mAP on mammograms while blocking irrelevant imaging inputs.
- Explainable AI in Speaker Recognition -- Making Latent Representations Understandable