A toolbox for spectral compressive imaging reconstruction including MST (CVPR 2022), CST (ECCV 2022), DAUHST (NeurIPS 2022), BiSCI (NeurIPS 2023), HDNet (CVPR 2022), MST++ (CVPRW 2022), etc.

Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

A Toolbox for Binarized Spectral Compressive Imaging (NeurIPS 2023)

This repository containts the pytorch scripts to train mixed-precision networks for microcontroller deployment, based on the memory contraints of the target device.

Official PyTorch repository for Quaternion Generative Adversarial Networks.

Scalable Quantum Neural Network builds and trains a large-scale QNN in a modular fashion. SQNN is evaluated with a binary classification task on the MNIST dataset.

Model-to-NPU pipelines for Qualcomm Snapdragon: QNN/ONNX/Android runtimes for on-device image and video generation.

Testing and playing around with QNNs using the mnist dataset

An HW-SW codesign tool to develeop and deploy MIxed-Precision QNN on PULP-based SoC's.

QNN 1 Neural Network Regressor qiskit

A modular and extensible quantum machine learning framework supporting customizable models, encoders, kernels, and quantum providers for research and prototyping.

Patched Qualcomm AI Stack SDK fixing critical memory corruption and shape inference bugs in model converter tools (QNN/SNPE).

Comparative analysis of CNN and Hybrid Quantum Neural Network (QNN) architectures for electrical resistivity prediction using synthetically generated ERT data. Includes data generation, preprocessing, classical deep learning, quantum-enhanced modeling, and performance evaluation.

Quantum Neural Network Regressor (QNN Regressor) - Variational Quantum Regressor (VQR)