The Quantum Shortcut: Complex Phase-State Dynamics Reduce the Optimization Steps of Sequence Models

• URL: http://arxiv.org/abs/2608.14691v1
• Date: Fri, 07 Aug 2026 15:12:36 GMT
• Title: The Quantum Shortcut: Complex Phase-State Dynamics Reduce the Optimization Steps of Sequence Models
• Abstract summary: Sequence models are distinguished by their backbone, the mechanism that routes information across positions.<n>This paper varies a choice that is prior to the backbone and shared by nearly all current models.<n>We study a complex-valued alternative drawn from the mathematics of quantum theory, in which information is carried by the phases of the state.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sequence models are conventionally distinguished by their backbone, the mechanism that routes information across positions, such as attention or recurrence. This paper varies a choice that is prior to the backbone and shared by nearly all current models: the \emph{substrate}, the number system in which the hidden state is represented together with the form of the map from state to prediction. The prevailing substrate is a real-valued state with an affine--softmax readout; we study a complex-valued alternative drawn from the mathematics of quantum theory, in which information is carried by the phases of the state and scores are quadratic Born forms. Prior work proved an idealized version of this substrate representationally stronger than any real model with a linear readout; we ask whether it also trains faster. Relaxing the two properties that block deployment, exact unitarity and the Born vocabulary readout, we instantiate it in the Mamba state-space model and an attention-based Transformer. At 253M parameters, matched to within $0.02\%$ and trained under one fixed protocol on three byte-level corpora, the complex models reach every measured validation loss in approximately one third (state-space) and one half (attention) of the optimization steps of their real counterparts. The two backbones then diverge. Once the learning-rate warmup ends, the state-space advantage continues to widen, from $0.321$ to $0.354$ bits per character on OpenWebText and from $0.368$ to $0.396$ on FineWeb, which an artifact of the warmup ramp would not do; the attention advantage instead decays toward zero on every corpus, and is therefore an effect of early training.

Related papers

• Time-Frequency Geometric Cross-Attention for Chunked Vision-Language-Action Models [10.591519354017803]
  We show how to repair two blind spots in a vision--action (VLA) policy.<n>We use a drop-in module to fine-tune a pretrained VLA.<n>We show how TFGCA improves in-distribution LIBERO by +1.5 on average, the OOD LIBERO-Plus by +6.3, the randomized average under RoboTwin domain randomization by +28.5, and the overall success rate on three real-robot AgiBot A2 tasks by +11.67 points.
  arXiv  Detail & Related papers  (2026-09-09T09:16:49Z)
• Exact Fock-State Preparation with $n^{1/4}$ Circuit Depth [0.18049490005680832]
  We map Fock-state preparation in an infinite-dimensional Hilbert space onto two-dimensional amplitude amplification.<n>Phase matching guarantees unit fidelity in the ideal model; remarkably, preparing $|106rangle$ requires only 39 iterations.<n>This framework provides a broadly applicable route to highly excited bosonic states on platforms supporting these elementary controls.
  arXiv  Detail & Related papers  (2026-08-24T15:35:08Z)
• How Good Can Linear Models Be for Time-Series Forecasting? [1.558068541168739]
  We use Ridge regression as the testbed, since it has a closed-form solution and interpretable weights.<n>We search over context length, local normalization, regularization, and augmentation on eight standard benchmarks.<n>The resulting models beat prior linear forecasters on most dataset-horizon entries and exceed Transformer, CNN baselines on six of eight benchmarks.
  arXiv  Detail & Related papers  (2026-06-25T16:57:50Z)
• Simulating quantum circuits with a neural statebank [0.0]
  We introduce a neural statebank that learns a wavefunction along a quantum circuit trajectory.<n>On long-range circuits combining entanglement, magic, and non-diagonal branching, a statebank reaches $sim 10-2$ at 34 qubits.<n>The same architecture accurately simulates quantum approximate optimization, Clifford+$T$, and Clifford circuits.
  arXiv  Detail & Related papers  (2026-06-07T16:05:44Z)
• CAWN: Continuous Acoustic Wave Networks for Autoregressive Language Modeling [46.16066322190728]
  We introduce the Continuous Acoustic Wave Network (CAWN), a fully continuous sequence-mixing architecture.<n>Instead of discrete matrix-based attention, CAWN projects hidden states into multi-headed complex-domain phasors.<n>To prevent signal degradation over ultra-long contexts, we introduce a dual-gated Selective Phase Resonance mechanism.
  arXiv  Detail & Related papers  (2026-04-05T20:13:22Z)
• H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers [124.11648300910444]
  We present a hierarchical plug-and-play pruning-and-$-recovering framework, called Hierarchical Hourglass Tokenizer (H$_2$OT)<n>Our method is general-purpose: it can be easily incorporated into common VPT models on both seq2seq and seq2frame pipelines.
  arXiv  Detail & Related papers  (2025-09-08T17:59:59Z)
• Subspace Variational Quantum Simulation: Fidelity Lower Bounds as Measures of Training Success [4.387699521196243]
  We propose an iterative variational quantum algorithm to simulate the time evolution of arbitrary initial states within a given subspace.<n>The algorithm compresses the Trotter circuit into a shorter-depth parameterized circuit, which is optimized simultaneously over multiple initial states.<n>We show our cost function exhibits a barren-plateau-free region near the initial parameters at each iteration in the training landscape.
  arXiv  Detail & Related papers  (2025-09-08T06:22:00Z)
• Holistic Surgical Phase Recognition with Hierarchical Input Dependent State Space Models [56.2236083600999]
  We propose a novel hierarchical input-dependent state space model for surgical video analysis.<n>Our framework incorporates a temporally consistent visual feature extractor, which appends a state space model head to a visual feature extractor to propagate temporal information.<n> Experiments have shown that our method outperforms the current state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2025-06-26T14:43:57Z)
• Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports [53.637837706712794]
  We propose a Unified Trajectory Generation model, UniTraj, that processes arbitrary trajectories as masked inputs.<n>Specifically, we introduce a Ghost Spatial Masking (GSM) module, embedded within a Transformer encoder, for spatial feature extraction.<n>We benchmark three practical sports datasets, Basketball-U, Football-U, and Soccer-U, for evaluation.
  arXiv  Detail & Related papers  (2024-05-27T22:15:23Z)
• DiffComplete: Diffusion-based Generative 3D Shape Completion [114.43353365917015]
  We introduce a new diffusion-based approach for shape completion on 3D range scans. We strike a balance between realism, multi-modality, and high fidelity. DiffComplete sets a new SOTA performance on two large-scale 3D shape completion benchmarks.
  arXiv  Detail & Related papers  (2023-06-28T16:07:36Z)
• Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost [53.746169882193456]
  Recent works have proposed various sparse attention modules to overcome the quadratic cost of self-attention. We propose a model that resolves both problems by endowing each attention head with a mixed-membership Block Model. Our model outperforms previous efficient variants as well as the original Transformer with full attention.
  arXiv  Detail & Related papers  (2022-10-27T15:30:52Z)
• NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go [109.88509362837475]
  We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes. NeuroMorph produces smooth and point-to-point correspondences between them. It works well for a large variety of input shapes, including non-isometric pairs from different object categories.
  arXiv  Detail & Related papers  (2021-06-17T12:25:44Z)
• Neural networks behave as hash encoders: An empirical study [79.38436088982283]
  The input space of a neural network with ReLU-like activations is partitioned into multiple linear regions. We demonstrate that this partition exhibits the following encoding properties across a variety of deep learning models. Simple algorithms, such as $K$-Means, $K$-NN, and logistic regression, can achieve fairly good performance on both training and test data.
  arXiv  Detail & Related papers  (2021-01-14T07:50:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.