Quantum Masked Autoencoders: Filling in the Blanks on Quantum Hardware

Kari Jaaskelainen

24 Nov 2025 — 1 min read

Quantum AIs that fill in the blanks

Masked autoencoders help AI learn from images with missing pieces. This paper brings that idea to quantum computing with Quantum Masked Autoencoders (QMAEs)—models that learn and reconstruct missing features directly within quantum states, not just classical embeddings.

How it works: parts of an image are masked; a quantum encoder-decoder learns to recover them, improving the full image reconstruction.
Why it matters: more robust quantum vision models could make better use of limited, noisy quantum hardware.
Results: on MNIST digits, QMAE rebuilt masked images with clearer visual quality and achieved, on average, 12.86% higher classification accuracy than state-of-the-art quantum autoencoders when masks were present.

Authors: Emma Andrews, Prabhat Mishra. Categories: quant-ph, cs.AI, cs.LG. Paper: https://arxiv.org/abs/2511.17372v1

Paper: https://arxiv.org/abs/2511.17372v1

Register: https://www.AiFeta.com

#QuantumComputing #AI #MachineLearning #ComputerVision #Autoencoders #QuantumAI #MNIST #Research

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Quantum AIs that fill in the blanks

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A