quant-phJun 22, 2026

Recursive QLSTM with Dynamic Variational Quantum Circuit Adaptation

Authors: Samuel Yen-Chi Chen, Yifeng Peng, Jiun-Cheng Jiang, Chun-Hua Lin, Kuo-Chung Peng, Junghoon Justin Park, Huan-Hsin Tseng, Hsin-Yi Lin, +3 more

Organizations: Wells Fargo · Stevens Institute of Technology · National Taiwan University · Seoul National University · Brookhaven National Laboratory · Imperial College London

Abstract

Recent advances in quantum computing and machine learning have motivated the development of quantum models for sequential data processing. In this paper, we propose a Recursive Quantum Long Short-Term Memory model, or Recursive QLSTM, which extends QLSTM through metacore-based recursive constructions. We numerically test the model under different input sequence lengths, metacore designs, and recursive rules, and identify the best-performing architecture among these variants. For this selected model, we further provide theoretical arguments explaining why its recursive structure improves temporal information propagation and enhances learning performance. Our results suggest that Recursive QLSTM offers a flexible and effective framework for quantum recurrent learning over input time series of various lengths.

Explore similar work

CardsList

  1. Recursive Quantum Long Short-Term Memory for Stable Short-Horizon Temperature Forecasting

    Sep 17, 2026Mu-En Lee, Yen-Ku Liu, Samuel Yen-Chi Chen +1Hybrid Quantum Neural NetworksBidirectional Long Short-Term Memory

  2. QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling

    May 13, 2026Hoang-Quan Nguyen, Sankalp Pandey, Khoa LuuSequence ModelingMemory-Augmented Large Language Models

  3. Self-Modulating Quantum Fast-Weight Programmers for Efficient Adaptive Sequential Learning

    Jun 22, 2026Samuel Yen-Chi Chen, Yifeng Peng, Kuo-Chung Peng +8Quantum Machine LearningModifications