A Faster R-CNN detector paired with a Transformer-augmented MLP reconstructs parent-child lineages during ligament fragmentation from impinging jet images, achieving 0.872 F1 for detection and 86.1% association accuracy with perfect fragmentation recall.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
An encoded FBSNN uses tensor encoding of inputs as images and CNN processing to approximate high-dimensional BSDEs more efficiently than vanilla FBSNN.
Student models distilled from code language models often fail to deeply mimic teachers, showing up to 62% behavioral discrepancies and 285% worse drops under attacks that accuracy metrics miss.
A temperature-scaled hybrid fusion of ResNet and trainable quantum circuit features reaches 87.82% accuracy on BreastMNIST, outperforming classical baselines.
DeepONet surrogate model accurately predicts wave-induced radiation stress and wave heights in steady-state simulations as a replacement for the SWAN numerical model.
citing papers explorer
-
Deep Learning-Based Tracking and Lineage Reconstruction of Ligament Breakup
A Faster R-CNN detector paired with a Transformer-augmented MLP reconstructs parent-child lineages during ligament fragmentation from impinging jet images, achieving 0.872 F1 for detection and 86.1% association accuracy with perfect fragmentation recall.
-
Encoded Forward Backward Stochastic Neural Network for High-Dimensional Backward Stochastic Differential Equations and Parabolic Partial Differential Equations
An encoded FBSNN uses tensor encoding of inputs as images and CNN processing to approximate high-dimensional BSDEs more efficiently than vanilla FBSNN.
-
A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?
Student models distilled from code language models often fail to deeply mimic teachers, showing up to 62% behavioral discrepancies and 285% worse drops under attacks that accuracy metrics miss.
-
On the Complementarity of Quantum and Classical Features: Adaptive Hybrid Quantum-Classical Feature Fusion for Breast Cancer Classification
A temperature-scaled hybrid fusion of ResNet and trainable quantum circuit features reaches 87.82% accuracy on BreastMNIST, outperforming classical baselines.
-
Operator Learning for Surrogate Modeling of Wave-Induced Forces from Sea Surface Waves
DeepONet surrogate model accurately predicts wave-induced radiation stress and wave heights in steady-state simulations as a replacement for the SWAN numerical model.