RiverONE: Generating Knowledge-Intensive VLM by Simulated Quantum Machines

• URL: http://arxiv.org/abs/2606.29966v1
• Date: Mon, 29 Jun 2026 08:44:11 GMT
• Title: RiverONE: Generating Knowledge-Intensive VLM by Simulated Quantum Machines
• Abstract summary: RiverONE is a lightweight vision-language model for quantum calibration plot understanding.<n>We use simulated quantum computation to generate structured parameters for compact classical AI systems.<n>With approximately 1.9 billion parameters, RiverONE achieves at least 95% of the performance of NVIDIA Ising 1 on quantum calibration plot understanding tasks.
• Score: 10.511025230975681
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Qiboml: towards the orchestration of quantum-classical machine learning [53.28668485072944]
  We present Qiboml, an open-source software library for orchestrating quantum and classical machine learning.<n>We showcase its functionalities, including diverse simulation options, noise-aware simulations and real-time error mitigation and calibration.
  arXiv  Detail & Related papers  (2025-10-13T18:00:00Z)
• Quantum Visual Fields with Neural Amplitude Encoding [70.86293548779774]
  We introduce a new type of Quantum Implicit Neural Representation (QINR) for 2D image and 3D geometric field learning.<n>QVF encodes classical data into quantum statevectors using neural amplitude encoding grounded in a learnable energy manifold.<n>Our ansatz follows a fully entangled design of learnable parametrised quantum circuits, with quantum (unitary) operations performed in the real Hilbert space.
  arXiv  Detail & Related papers  (2025-08-14T17:59:52Z)
• Minimal Quantum Reservoirs with Hamiltonian Encoding [72.27323884094953]
  We investigate a minimal architecture for quantum reservoir computing based on Hamiltonian encoding.<n>This approach circumvents many of the experimental overheads typically associated with quantum machine learning.
  arXiv  Detail & Related papers  (2025-05-28T16:50:05Z)
• Training quantum machine learning models on cloud without uploading the data [0.0]
  We propose a method that runs the parameterized quantum circuits before encoding the input data. This enables a dataset owner to train machine learning models on quantum cloud platforms. It is also capable of encoding a vast amount of data effectively at a later time using classical computations.
  arXiv  Detail & Related papers  (2024-09-06T20:14:52Z)
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [62.46800898243033]
  Recent progress in quantum learning theory prompts a question: can linear properties of a large-qubit circuit be efficiently learned from measurement data generated by varying classical inputs?<n>We prove that the sample complexity scaling linearly in $d$ is required to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d.<n>We propose a kernel-based method leveraging classical shadows and truncated trigonometric expansions, enabling a controllable trade-off between prediction accuracy and computational overhead.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• Quantum Machine Learning: from physics to software engineering [58.720142291102135]
  We show how classical machine learning approach can help improve the facilities of quantum computers. We discuss how quantum algorithms and quantum computers may be useful for solving classical machine learning tasks.
  arXiv  Detail & Related papers  (2023-01-04T23:37:45Z)
• Quantum neural networks [0.0]
  This thesis combines two of the most exciting research areas of the last decades: quantum computing and machine learning. We introduce dissipative quantum neural networks (DQNNs), which are capable of universal quantum computation and have low memory requirements while training.
  arXiv  Detail & Related papers  (2022-05-17T07:47:00Z)
• TensorLy-Quantum: Quantum Machine Learning with Tensor Methods [67.29221827422164]
  We create a Python library for quantum circuit simulation that adopts the PyTorch API. Ly-Quantum can scale to hundreds of qubits on a single GPU and thousands of qubits on multiple GPU.
  arXiv  Detail & Related papers  (2021-12-19T19:26:17Z)
• Large-scale quantum machine learning [0.0]
  We measure quantum kernels using randomized measurements to gain a quadratic speedup in time and quickly process large datasets. We efficiently encode high-dimensional data into quantum computers with the number of features scaling linearly with the circuit depth. Using currently available quantum computers, the MNIST database can be processed within 220 hours instead of 10 years.
  arXiv  Detail & Related papers  (2021-08-02T17:00:18Z)
• QuClassi: A Hybrid Deep Neural Network Architecture based on Quantum State Fidelity [13.152233840194473]
  We propose a novel architecture QuClassi, a quantum neural network for both binary and multi-class classification. Powered by a quantum differentiation function along with a hybrid quantum-classic design, QuClassi encodes the data with a reduced number of qubits and generates the quantum circuit, pushing it to the quantum platform for the best states.
  arXiv  Detail & Related papers  (2021-03-21T05:28:37Z)
• Application of Quantum Machine Learning using the Quantum Variational Classifier Method to High Energy Physics Analysis at the LHC on IBM Quantum Computer Simulator and Hardware with 10 qubits [6.56216604465389]
  Quantum machine learning could become a powerful tool for data analysis in high energy physics. We employ the quantum variational classifier method in two recent LHC flagship physics analyses. We foresee the usage of quantum machine learning in future high-luminosity LHC physics analyses.
  arXiv  Detail & Related papers  (2020-12-21T18:39:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.