RiverONE: Generating Knowledge-Intensive VLM by Simulated Quantum Machines
2026-06-29 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors created a new vision-language model called RiverONE to understand quantum calibration plots. They used simulated quantum computing to help build the model's parameters, but the model runs on regular computers without needing quantum hardware. RiverONE is much smaller than a comparable model but still performs nearly as well on specific quantum tasks. This shows that simulated quantum computation can help make smaller, efficient AI models for scientific problems.
quantum computingvision-language modelsimulated quantum computationquantum calibrationparameter compressionvisual encoderInternVLclassical GPUscientific AI modelsquantum hardware
Authors
Xindian Ma, Xinyu Long, Yefei Zhang, Yanchen Liu, Xianghao Li, Yufu Wen, Yike Hu, Yuedong Zhu, Zeyang Ma, Wen Qin, Yikun Wang, Peng Yang, Monan Wang, Teng Yu
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.