We propose a quantum-inspired ensemble learning framework optimized for classifying imbalanced, high-dimensional datasets. The method improves minority class detection, ensemble stability, and generalization without increasing computational burden.

Aditya Kulkarni, Liang Qiu, Martina Rossi, Rahul Shetty

This research presents a novel convolutional transformer hybrid network designed for real-time image recognition on constrained edge devices. The model balances accuracy and efficiency, outperforming standard baselines in resource-limited environments.

Nathan Brooks, Emily Peterson, Ryan Summers

A novel few-shot learning strategy is introduced using attention-guided memory replay to enable effective cross-domain adaptation. The technique shows marked performance improvements on several transfer learning benchmarks with minimal labeled samples.

Chen Lei, Wu Jiahui, Gao Xinyi, Xu Peng

This study proposes a graph neural network architecture integrated with attention mechanisms and transfer learning to improve multimodal sensor data interpretation. The system demonstrates high adaptability, reduced error rates, and efficient training across diverse datasets collected from dynamic, real-time environments.

Ramnath Iyer, Anna Schmidt, James Wilson, Fatima Noor, Vikram Sinha, Carlos Martinez

This paper introduces a privacy-preserving federated learning system designed to enable collaborative intelligence without centralizing user data. The framework improves communication efficiency, ensures scalable deployment, and achieves near-centralized accuracy levels across various benchmark tasks under limited network and data conditions.

Michael Scott, Olivia Adams, David Harris, Emma Walker, Thomas Green

We present a novel method for generating cross-modal embeddings to improve context-aware retrieval in high-dimensional systems. Using attention-guided learning and latent alignment, the approach improves semantic understanding and performance in retrieval tasks with minimal labeled training data.

Chen Yu, Gao Jie, Zhang Wei, Liu Chen, Huang Lei, Li Fang