# Quantum Attention by Overlap Interference: Predicting Classical and Many-Body Quantum Sequences

arXiv: https://arxiv.org/abs/2602.06699 · HTML: https://mlsanity.com/paper/2602.06699/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Challenges and Opportunities in Quantum Machine Learning](https://mlsanity.com/paper/2303.09491/) (2023)
- [Quantum Vision Transformers](https://mlsanity.com/paper/2209.08167/) (2022)
- [QKSAN: A Quantum Kernel Self-Attention Network](https://mlsanity.com/paper/2308.13422/) (2023)
- [Variational quantum simulation: a case study for understanding warm starts](https://mlsanity.com/paper/2404.10044/) (2024)
- [GQHAN: A Grover-inspired Quantum Hard Attention Network](https://mlsanity.com/paper/2401.14089/) (2024)
- [A learning theory for quantum photonic processors and beyond](https://mlsanity.com/paper/2209.03075/) (2022)
- [Reinforcement-learning calibration of coherent-state receivers on variable-loss optical channels](https://mlsanity.com/paper/2203.09807/) (2022)

## Abstract (arXiv)

We propose a variational quantum implementation of self-attention (QSA)-the core operation in transformers and large language models-which predicts future elements of a sequence by forming overlap-weighted combinations of past data. At variance with previous approaches, our QSA realizes the required nonlinearity through interference of state overlaps and a degree-k polynomial kernel, and estimates a loss based on R'enyi-1/2 entropic functionals via two observables' expectation values, avoiding the decoding of amplitude-encoded predictions into classical probabilities. QSA also accommodates a constrained, trainable data-embedding tying state overlaps to data-level similarities. Its dominant end-to-end training complexity scales as Oleft(μ-1k2Tdright), versus Oleft(T dk+1right) of the fairest classical comparison, with μ a training signal; we show numerically that this allows a complexity advantage in the regime where sequence length T dominates the embedding size d. In simulations, our QSA-based quantum transformer learns sequence prediction on classical data and on many-body transverse-field Ising trajectories-establishing trainable attention as a practical primitive for quantum dynamical modeling.