RiverONE: Generating Knowledge-Intensive VLM by Simulated Quantum Machines

2026-06-29

AI Summary

This work addresses the task of quantum calibration chart understanding by proposing RiverONE, a lightweight vision-language model capable of efficient inference without access to real quantum hardware. The approach innovatively leverages simulated quantum computation as a model construction mechanism to generate structured, quantum-inspired parameters, integrating a specialized vision encoder with the InternVL language backbone. Through parameter compression and knowledge distillation, RiverONE achieves at least 95% of the performance of NVIDIA Ising Calibration 1 while containing only 1.9 billion parameters—less than 10% of the latter’s size—demonstrating a remarkable balance between model compactness and representational capacity.

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.

Problem

• vision-language model
• quantum calibration plot
• lightweight AI
• knowledge-intensive VLM
• parameter efficiency

Innovation

• simulated quantum computation
• knowledge-intensive VLM
• quantum-generated parameters
• lightweight vision-language model
• quantum calibration plot understanding