Modern computer vision models are often too heavy to deploy on edge hardware. This work shows how quantum-inspired compression shrinks a high-fidelity model by 95%, from 258 MB to 8 MB, while preserving accuracy.
We ran inference with quantum circuits embedded inside a large language model, executed on a real superconducting quantum computer.
As scaling past a thousand GPUs exposed the limits of single-cloud strategies, this work shows how a cloud-agnostic orchestration layer doubled our utilization, turning the same hardware budget into twice the experiments.
As quantum computing advances threaten to expose today's encrypted traffic years from now, this work presents a practical, step by step path to PQC for the IoT, validated end to end on a low-cost edge device.
How can AI detect the unexpected without labeled data? We present a self-supervised pipeline for autonomous driving that learns normal road behavior, compressed 83% with quantum-inspired techniques for the edge.
Learn how Hypernova-60B v2602 adds robust tool-calling while preserving frontier-level intelligence at half the size, delivering agent-ready AI on a single GPU.
CEAMSA Singularity Food ha sido desarrollado con una idea clara: Poder estimar propiedades físico-químicas del producto antes de fabricarlo, a partir de la receta y la selección de lotes. Durante el proyecto se consolidó una base de datos integrada y se probó, de forma comparativa, un conjunto de modelos (incluyendo enfoques quantum-inspired) para entender hasta dónde es posible llegar en un entorno industrial real. El resultado es doble: por un lado, una plataforma de predicción lista para integrarse; por otro, un marco de trabajo que ayuda a tomar decisiones con más información, reducir incertidumbre y preparar el terreno para pasos posteriores como optimización de planificación y calidad.
This study conducted by Sopra Steria evaluates the performance of a compression method, called CompactifAI, developed by Multiverse Computing, applied to the large language model Llama 3.1 8B. The evaluation focused on model efficiency (in terms of energy consumption) and accuracy using respectively the frameworks Codecarbon and Ragas. A comparison was performed between the model compressed with CompactifAI and its full-size version. The findings reveal that the compressed model using CompactifAI not only significantly reduced the computational resources but also maintained the model accuracy, making the model more efficient, scalable and cost-effective.
Large Language Models (LLMs) such as ChatGPT and LlaMA are advancing rapidly in generative Artificial Intelligence (AI), but their immense size poses significant challenges, such as huge training and inference costs, substantial energy demands, and limitations for on-site deployment. Traditional compression methods such as pruning, distillation, and low-rank approximation focus on reducing the effective number of neurons in the network, while quantization focuses on reducing the numerical precision of individual weights to reduce the model size while keeping the number of neurons fixed. While these compression methods have been relatively successful in practice, there’s no compelling reason to believe that truncating the number of neurons is an optimal strategy. In this context, this paper introduces CompactifAI, an innovative LLM compression approach using quantum-inspired Tensor Networks that focuses on the model’s correlation space instead, allowing for a more controlled, refined and interpretable model compression. Our method is versatile and can be implemented with — or on top of — other compression techniques. As a benchmark, we demonstrate that CompactifAI alone enables compression of the LlaMA-2 7B model to only 30% of its original size while recovering over 90% of the original accuracy after a brief distributed retraining.
Large financial institutions play an important role in driving society’s sustainability goals. Banks and hedge funds can support the decarbonization of industrial and institutional clients while also influencing capital flows through advice to individual clients. For example, financial institutions can increase the credit availability for corporate energy transition actions. At the individual level, banks and investor advisors can help clients who want to enhance the environmental, social and governmental (ESG) profile of their investments.
Quantum Computing impacts business transformation in firms and requires a new mindset for operational excellence.
Here we introduce an improved approach to Variational Quantum Attack Algorithms (VQAA) on crytographic protocols. Our methods provide robust quantum attacks to well-known cryptographic algorithms, more efficiently and with remarkably fewer qubits than previous approaches. We implement simulations of our attacks for symmetric-key protocols such as S-DES, S-AES and Blowfish. For instance, we show how our attack allows a classical simulation of a small 8-qubit quantum computer to find the secret key of one 32-bit Blowfish instance with 24 times fewer number of iterations than a brute-force attack. Our work also shows improvements in attack success rates for lightweight ciphers such as S-DES and S-AES. Further applications beyond symmetric-key cryptography are also discussed, including asymmetric-key protocols and hash functions. In addition, we also comment on potential future improvements of our methods. Our results bring one step closer assessing the vulnerability of large-size classical cryptographic protocols with Noisy Intermediate-Scale Quantum (NISQ) devices, and set the stage for future research in quantum cybersecurity.
We efficiently simulate IBM's largest quantum processors, Eagle, Osprey, and Condor, using graph-based Projected Entangled Pair States, achieving unprecedented accuracy with simple tensor updates.
Quantum error correction through surface codes, critical for reliable quantum computing, demands efficient decoding algorithms balancing speed, complexity, and accuracy.
Paper by Gianni del Bimbo, Daniel García Guijo and Esperanza Cuenca Gómez.
Case Study by Gianni del Bimbo, Rodrigo Hernández Cifuentes, Esperanza Cuenca Gómez, Daniel García Guijo and Angus Dunnett
The Cheyette model is a quasi-Gaussian volatility interest rate model widely used to price interest rate derivatives such as European and Bermudan Swaptions for which Monte Carlo simulation has become the industry standard.
How quantum-inspired algorithms solve the most complex PDE and machine learning problems to achieve real business advantage now.
Machine learning algorithms, both in their classical and quantum versions, heavily rely on optimization algorithms based on gradients, such as gradient descent and alike.
A Practical Approach by Esperanza Cuenca Gómez and Pablo Martín Ramiro