Quantum computing provides a powerful paradigm for representing and transforming high-dimensional information through superposition, entanglement, and measurement-induced nonlinear features. While current quantum hardware is not yet practical for direct large-scale vision-language model (VLM) inference, simulated quantum computation can be used during model construction to generate structured parameters for compact classical AI systems. We build RiverONE, a lightweight vision-language model for quantum calibration plot understanding, using simulated quantum computation. It employs a specialized visual encoder and an InternVL-based language backbone. To compensate for compression-induced information loss, we introduce quantum-generated parameters, which are materialized as classical tensors after training. This allows RiverONE to run entirely on classical GPUs at inference time, with no quantum hardware or runtime quantum simulation. With approximately 1.9 billion parameters, RiverONE achieves at least 95\% of the performance of NVIDIA Ising Calibration 1 on quantum calibration plot understanding tasks while using less than 10\% of its parameter count. These results suggest that simulated quantum computation can serve as a practical construction-stage mechanism for building lightweight, knowledge-intensive scientific VLMs. Our code is available at https://github.com/THeWakeSystems/RiverOne.
Quantum computing provides a powerful paradigm for representing and transforming high-dimensional information through superposition, entanglement, and measurement-induced nonlinear features. While current quantum hardware is not yet practical for direct large-scale vision-language model (VLM) inference, simulated quantum computation can be used during model construction to generate structured parameters for compact classical AI systems. We build RiverONE, a lightweight vision-language model for quantum calibration plot understanding, using simulated quantum computation. It employs a specialized visual encoder and an InternVL-based language backbone. To compensate for compression-induced information loss, we introduce quantum-generated parameters, which are materialized as classical tensors after training. This allows RiverONE to run entirely on classical GPUs at inference time, with no quantum hardware or runtime quantum simulation. With approximately 1.9 billion parameters, RiverONE achieves at least 95% of the performance of NVIDIA Ising Calibration 1 on quantum calibration plot understanding tasks while using less than 10% of its parameter count. These results suggest that simulated quantum computation can serve as a practical construction-stage mechanism for building lightweight, knowledge-intensive scientific VLMs. Our code is available at https://github.com/THeWakeSystems/RiverOne.
As quantum computing moves from the noisy intermediate-scale quantum (NISQ) era toward early fault-tolerant quantum computing (EFTQC), quantum-enhanced AI is shifting from a conceptual idea to experimental research. Quantum components are expected to extend the capabilities of existing AI systems, yet it remains unclear how such components will help within large multimodal models. In this study, we try to answer that question for vision-language models (VLMs) using classically simulated quantum layers. With LLaVA-OneVision as the backbone, we evaluate 4- and 8-qubit basic-ring and strongly entangling circuits at four insertion and four replacement locations. Insertion adds quantum layers to the classical model, while replacement substitutes them for classical components. Using the same setup, we compare performance and computational cost between classical and quantum-classical hybrid models. On the Visual Spatial Reasoning dataset, inserting a quantum layer after the visual projector reaches 80.7% development accuracy, 2.28 percentage-points above classical full fine-tuning. Replacing the final decoder feed-forward sublayer retains 79.22% accuracy with 13.07 million fewer trainable parameters. Quantum insertion can thus improve accuracy, and selective replacement can reduce parameters. These benefits depend strongly on where the quantum layer is inserted or which classical component it replaces: earlier replacements lower accuracy, and fewer parameters do not reliably shorten training or reduce computation. To assess potential security benefits, we evaluated the robustness of quantum-classical hybrid models under six attack settings. Overall, our study maps where quantum layers help and hurt within VLMs, offering a starting point for hybrid VLM design; whether these gains generalize remains open. The code is available at https://github.com/TITANS-Lab-Artifacts/QuantumVLM.
As foundational tools in natural language processing, Large Language Models (LLMs) have immense parameter scales, which makes deployment and inference increasingly prohibitive, especially in resource-constrained devices. Therefore, knowledge distillation for LLMs, i.e., compressing the LLM to a smaller model, is meaningful. With strong parameter representation capacity, quantum computing is regarded as a promising solution. Here, we propose a Quantum knowledge Distillation model for LLMs (QD-LLM) that leverages variational quantum circuits to learn from LLMs. In classical simulation, QD-LLM outperforms several mainstream distillation methods on multiple text classification tasks in terms of both accuracy and efficiency using only 11 qubits. The results reveal an interesting phenomenon that the simulation of quantum student models may be regarded as a new class of quantum-inspired classical algorithms. Remarkably, we deploy the obtained circuits on the Baihua superconducting quantum processor via the Quafu platform to assess practical feasibility. The model maintains stable inference performance despite hardware constraints such as decoherence and finite sampling. In summary, QD-LLM marks a foundational step in connecting quantum computing with LLMs, demonstrating the feasibility of quantum-native approaches that aim to compress and deploy models of increasingly larger scales. The code of this article has been open-sourced at https://github.com/Lilingxiao-bupt/QD-LLM.
The remarkable success of large language models (LLMs) in code generation has transformed software development, with systems like Codex, CodeGen, and StarCoder demonstrating strong capabilities in synthesizing functional code from natural language descriptions. However, this progress comes at a steep computational cost. Modern code generation models require hundreds of millions to billions of parameters—GPT-3 contains 175 billion parameters, CodeGen-16B uses 16 billion, and the trend continues toward ever-larger models. This scale creates fundamental challenges in training cost, inference latency, memory consumption, and environmental impact. We present a quantum transfer learning framework as an alternative approach to classical model compression for code generation. By replacing selected MLP layers with variational quantum circuits (VQCs), we exploit the exponential representational capacity of quantum systems to achieve Θ(DlogD) parameter scaling instead of classical Θ(D2) . Our hybrid classical-quantum architecture balances three competing objectives: leveraging existing pre-trained knowledge, achieving parameter compression through quantum representation, and maintaining compatibility with near-term quantum hardware constraints. We demonstrate our approach on CodeGen-350M, a production-scale code generation model, adopting a bottleneck architecture that substantially reduces parameters compared to the original MLP layer. Through a fair comparison against a classical bottleneck baseline with near-identical parameter count, we show that the VQC achieves superior representational quality—lower perplexity and higher code generation accuracy—validating the quantum layer’s expressivity advantage in the compressed latent space. Our design employs data re-uploading, where classical input features are re-encoded at each variational layer via trainable RY gates, enhancing the circuit’s expressive power on near-term devices.
Abstract Quantum machine learning (QML) presents potential for early industrial adoption, yet limited access to quantum hardware remains a significant bottleneck for deployment of QML solutions. This work explores the use of classical surrogates to bypass this restriction, which is a technique that allows to build a lightweight classical representation of a (trained) quantum model, enabling to perform inference on entirely classical devices. We reveal prohibitive high computational demand associated with previously proposed methods for generating classical surrogates from quantum models, and propose an alternative pipeline enabling generation of classical surrogates at a larger scale than was previously possible. Previous methods required at least a high-performance computing (HPC) system for quantum models of below industrial scale (ca. 20 qubits), which raises questions about its practicality. We greatly minimize the redundancies of the previous approach, utilizing only a minute fraction of the resources previously needed. We demonstrate the effectiveness of our method on a real-world energy demand forecasting problem, conducting rigorous testing of performance and computation demand in both simulations and on quantum hardware. Our results indicate that our method achieves high accuracy on the testing dataset while its computational resource requirements scale polynomially rather than exponentially. This work presents a lightweight approach to transform quantum solutions into classically deployable versions, facilitating faster integration of quantum technology in industrial settings. Furthermore, it can serve as a powerful research tool in search of a practical quantum advantage in an empirical setup.
The convergence of quantum computing and artificial intelligence represents a paradigm shift in computational capability, enabling solutions to previously intractable optimization problems, accelerated machine learning training, and enhanced natural language understanding through quantum state exploitation. This paper presents a comprehensive framework encompassing five distinct quantum artificial intelligence architectures: Quantum Machine Learning utilizing quantum circuit-based training and inference, Quantum-Inspired AI implementing quantum algorithmic principles on classical hardware, Hybrid Quantum-Classical AI leveraging collaborative processing between central processing units and quantum processing units, Quantum Optimization AI for solving complex combinatorial problems, and Quantum Natural Language Processing exploiting quantum superposition for semantic reasoning. The quantum machine learning architecture implements variational quantum eigensolvers and quantum kernel methods for feature space transformation, achieving exponential speedup in specific classification tasks. The quantum-inspired approach applies tensor network decomposition and quantum annealing simulation on classical systems, demonstrating polynomial speedup for optimization problems. The hybrid quantum-classical framework orchestrates workload partitioning between conventional processors and quantum accelerators through dynamic task allocation algorithms, optimizing for quantum circuit depth and classical preprocessing overhead. Quantum optimization leverages quantum annealing and quantum approximate optimization algorithms for solving large-scale combinatorial problems in logistics, finance, and molecular simulation. Quantum natural language processing implements quantum word embeddings in Hilbert space, enabling superposition-based semantic analysis with logarithmic dimensional complexity compared to classical word vector representations. This research establishes theoretical foundations and architectural blueprints for quantum-enhanced artificial intelligence systems, positioning quantum computing as a transformative technology for next-generation machine learning, optimization, and cognitive computing applications.
Quantum computing calibration depends on interpreting experimental data, and calibration plots provide the most universal human-readable representation for this task, yet no systematic evaluation exists of how well vision-language models (VLMs) interpret them. We introduce QCalEval, the first VLM benchmark for quantum calibration plots: 243 samples across 87 scenario types from 22 experiment families, spanning superconducting qubits and neutral atoms, evaluated on six question types in both zero-shot and in-context learning settings. The best general-purpose zero-shot model reaches a mean score of 72.3, and many open-weight models degrade under multi-image in-context learning, whereas frontier closed models improve substantially. A supervised fine-tuning ablation at the 9-billion-parameter scale shows that SFT improves zero-shot performance but cannot close the multimodal in-context learning gap. As a reference case study, we release NVIDIA Ising Calibration 1, an open-weight model based on Qwen3.5-35B-A3B that reaches 74.7 zero-shot average score.