Quantum AI Report

The convergence of Quantum with AI

Riverlane

Riverlane develops quantum error correction software and the Deltaflow operating system for quantum computers. The company works with hardware developers to reduce error rates and build fault-tolerant systems, positioning itself as a key enabling layer in the quantum computing stack.

AI-written profile · not yet reviewed · 15 August 2026

Headquarters
Cambridge, United Kingdom
Founded
2016
Status
Private
error correctionalgorithms software

Coverage

arXiv quant-ph

Toward Uncertainty-Aware and Generalizable Neural Decoding for Quantum LDPC Codes

A new preprint on arXiv (v2) presents work toward neural decoders for quantum low-density parity-check (LDPC) codes that are both uncertainty-aware and generalizable. The authors argue that conventional QEC decoding algorithms face accuracy and overhead limitations, while existing machine-learning decoders lack two key properties the work aims to address.

OutlookPlausible

Within two years, uncertainty-aware neural decoders for small quantum LDPC codes could match or outperform belief propagation plus ordered statistics decoding in simulation, providing a calibrated measure of decoding reliability.

error correctionalgorithms softwareGoogle Quantum AIIBM QuantumRiverlane
arXiv quant-ph

Logical Neural Belief Propagation for Linear-Complexity Decoding of Surface Codes

A preprint posted to arXiv introduces a decoder called Logical Neural Belief Propagation for surface codes. The authors argue that conventional belief propagation decoders scale linearly but often lack the logical accuracy required for fault tolerance, and they propose a neural enhancement designed to operate at the logical level rather than only on physical syndromes. The abstract frames this as a method to combine linear decoding complexity with improved logical accuracy, though no benchmark results are detailed in the abstract.

OutlookLikely

The paper might trigger incremental improvements to existing neural decoders even if the full method is not adopted, by highlighting logical-level loss functions as a design principle.

error correctionalgorithms softwareGoogle Quantum AIIBM QuantumRiverlane
arXiv quant-ph

Neural decoders for subsystem many-hypercube codes

A preprint posted to arXiv's quantum physics section on 17 August 2026 introduces neural network decoders for subsystem many-hypercube codes. The work appears to propose learned decoders that infer the most likely error from syndrome data for this class of quantum error-correcting codes. No experimental implementation is indicated in the headline, so the contribution is likely algorithmic and numerical.

OutlookPlausible

Within two years, the trained decoder could be benchmarked against standard decoders on simulated code instances, establishing whether neural approaches offer a meaningful reduction in logical error rate for this family.

error correctionalgorithms softwareGoogle Quantum AIIBM QuantumQuantinuumRiverlane
arXiv quant-ph

Quantum error correction at ultra-low overhead

A preprint posted on arXiv introduces a new quantum error correction protocol or code construction that achieves ultra-low overhead, potentially reducing the number of physical qubits required per logical qubit by a large factor compared to leading codes like the surface code.

OutlookLikely

The proposed code can be benchmarked on existing small quantum processors within a year, validating its low-overhead promise and accelerating adoption in near-term error-correction pipelines.

error correctionalgorithms softwareGoogle Quantum AIIBMPsiQuantumQuantinuumRiverlane
arXiv quant-ph

QAdapt: A Noise-Adaptive Neural Pre-Decoding Framework for Quantum Error Correction

A research paper introduced QAdapt, a noise-adaptive neural pre-decoding framework for quantum error correction. The framework uses machine learning to dynamically adjust to changing noise characteristics, aiming to improve decoding accuracy and reduce logical error rates. The work appears on arXiv under quantum physics.

OutlookPlausible

QAdapt enables near-term noisy quantum devices to execute deeper circuits by reducing logical error rates through real-time noise adaptation.

error correctionalgorithms softwareGoogle Quantum AIIBM QuantumQuantinuumRiverlane