Quantum-inspired adaptive tiling for high-performance matrix multiplication. Uses WKB tunneling physics with the golden ratio to derive optimal tile sizes from real-time CPU state. 15%+ gains on legacy hardware. AVX2/FMA3 + OpenMP.

QIANets is a research project focused on leveraging quantum-inspired algorithms for efficient AI model compression. By integrating principles from quantum computing, QIANets aims to reduce model sizes while maintaining performance, enabling more scalable and energy-efficient AI systems. The research is recognized at NeurIPS 2024 ML and Compression.

A flexible framework for Multi-Objective Neural Architecture Search (NAS) in PyTorch. It implements and compares Quantum-Inspired (MO-QNAS) and classic Evolutionary Algorithms (GA, NSGA-II, NSGA-III) to optimize CNNs for multiple objectives like accuracy, model size, and inference time. Includes a module for post-hoc fairness evaluation.