A 4-qubit quantum predicate head in CFEN achieves 57.25% mR@100 on Visual Genome 150 long-tailed predicates versus 41.1% classical, using 96 parameters and 256x feature compression.
Quiet-sr: Quantum image enhancement transformer for single image super-resolution
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
On Iris-scale hybrid quantum neural networks, ZNE, PEC, DDD, and LRE do not reliably outperform the unmitigated noisy baseline across five simulated noise channels.
GAT-QNN uses a two-stage genetic algorithm to train macroCircuits and select efficient microCircuits for hybrid quantum neural networks, reporting 22-23% accuracy gains on 4-class MNIST across backends.
Systematic exploration of hybrid quantum neural networks on a CKD dataset finds that compact architectures with encodings like IQP and Ring entanglement deliver the best accuracy-robustness-efficiency trade-off.
citing papers explorer
-
QPredSGG: Hybrid Quantum Predicate Learning for Long-Tailed Scene Graph Generation
A 4-qubit quantum predicate head in CFEN achieves 57.25% mR@100 on Visual Genome 150 long-tailed predicates versus 41.1% classical, using 96 parameters and 256x feature compression.
-
Robustness Evaluation of Hybrid Quantum Neural Networks under Noise Models via System-Level Error Mitigation
On Iris-scale hybrid quantum neural networks, ZNE, PEC, DDD, and LRE do not reliably outperform the unmitigated noisy baseline across five simulated noise channels.
-
GAT-QNN: Genetic Algorithm-Based Training of Hybrid Quantum Neural Networks
GAT-QNN uses a two-stage genetic algorithm to train macroCircuits and select efficient microCircuits for hybrid quantum neural networks, reporting 22-23% accuracy gains on 4-class MNIST across backends.
-
Design Space Exploration of Hybrid Quantum Neural Networks for Chronic Kidney Disease
Systematic exploration of hybrid quantum neural networks on a CKD dataset finds that compact architectures with encodings like IQP and Ring entanglement deliver the best accuracy-robustness-efficiency trade-off.