Quantum X Labs Inc. (Nasdaq: QXL) announced progress on its AI-driven quantum error-correction program, disclosing results from two development steps conducted using Nvidia's CUDA-Q QEC software libraries and accelerated computing infrastructure.

The Tel Aviv-based company said it executed its Deep Quantum Error Correction (DQEC) workflow on an Nvidia GPU within an Amazon Web Services environment. QXL benchmarked its transformer-based QECCT decoder against the classical Minimum-Weight Perfect Matching decoder across toric-code noise configurations, with the QECCT decoder outperforming the classical method in selected simulated regimes.

QXL also tested synthetic surface-code configurations modeled on Google's public surface-code geometry across multiple code distances. The company said its QECCT decoder showed stable logical and bit error rates under varying physical error conditions in those scenarios.

The company described these results as an initial step in validating the approach within controlled simulation environments. Future work is expected to include extending evaluations to publicly available experimental datasets and refining data pipelines compatible with CUDA-Q QEC frameworks.

"These results are meaningful because they move our program from cloud deployment into measured decoder performance and a surface-code data pipeline," said Prof. Nir Sharon, Chief Quantum Technology Scientist at Quantum X Labs.

QXL's broader roadmap includes planned work with IQCC, a Quantum Machines company, to generate hardware-derived syndrome data on superconducting quantum processing hardware. The company said it is also reviewing potential applications for Nvidia Ising-based AI pre-decoder workflows and low-latency optimization across its program stages.

QXL's DQEC technology is based on a proprietary transformer architecture that uses error-correction code structure and syndrome information to predict logical corrections. The system is intended to support multiple stabilizer-code workflows and function as a full decoder, pre-decoder, or hybrid component within accelerated quantum error correction systems.