Thinking While Listening: Fast-Slow Recurrence for Long-Horizon Sequential Modeling

• URL: http://arxiv.org/abs/2604.01577v1
• Date: Thu, 02 Apr 2026 03:45:13 GMT
• Title: Thinking While Listening: Fast-Slow Recurrence for Long-Horizon Sequential Modeling
• Abstract summary: We extend the recent latent recurrent modeling to sequential input streams.<n>By interleaving fast, recurrent latent updates with self-organizational ability, our method facilitates the learning of stable internal structures that evolve alongside the input.
• Score: 39.56521605534737
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We extend the recent latent recurrent modeling to sequential input streams. By interleaving fast, recurrent latent updates with self-organizational ability between slow observation updates, our method facilitates the learning of stable internal structures that evolve alongside the input. This mechanism allows the model to maintain coherent and clustered representations over long horizons, improving out-of-distribution generalization in reinforcement learning and algorithmic tasks compared to sequential baselines such as LSTM, state space models, and Transformer variants.

Related papers

• Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems [30.037248637148693]
  Self-refining Neural Surrogate model (SNS) can be implemented as a standalone model or as a complementary model to existing neural surrogates.
  arXiv  Detail & Related papers  (2026-03-18T14:14:40Z)
• Towards Efficient and Stable Ocean State Forecasting: A Continuous-Time Koopman Approach [17.986879367736762]
  Continuous-Time Koopman Autoencoder (CT-KAE) is a lightweight surrogate model for long-horizon ocean state forecasting.<n>CT-KAE exhibits bounded error growth and stable large-scale statistics, in contrast to autoregressive Transformer baselines.<n>The model achieves orders-of-magnitude faster inference compared to the numerical solver.
  arXiv  Detail & Related papers  (2026-03-05T09:39:44Z)
• Koopman Autoencoders with Continuous-Time Latent Dynamics for Fluid Dynamics Forecasting [17.98687936773676]
  We introduce a continuous-time Koopman framework that models latent evolution through numerical integration schemes.<n>By allowing variable timesteps at inference, the method demonstrates robustness to temporal resolution and generalizes beyond training regimes.<n>We evaluate the approach on classical CFD benchmarks and report accuracy, stability, and extrapolation properties.
  arXiv  Detail & Related papers  (2026-02-02T21:33:07Z)
• Sequential-Parallel Duality in Prefix Scannable Models [68.39855814099997]
  Recent developments have given rise to various models, such as Gated Linear Attention (GLA) and Mamba.<n>This raises a natural question: can we characterize the full class of neural sequence models that support near-constant-time parallel evaluation and linear-time, constant-space sequential inference?
  arXiv  Detail & Related papers  (2025-06-12T17:32:02Z)
• Continual Learning in Vision-Language Models via Aligned Model Merging [84.47520899851557]
  We present a new perspective based on model merging to maintain stability while still retaining plasticity.<n>To maximize the effectiveness of the merging process, we propose a simple mechanism that promotes learning aligned weights with previous ones.
  arXiv  Detail & Related papers  (2025-05-30T20:52:21Z)
• Generative Models for Long Time Series: Approximately Equivariant Recurrent Network Structures for an Adjusted Training Scheme [4.327763441385371]
  We present a simple yet effective generative model for time series data based on a Variational Autoencoder (VAE) with recurrent layers.<n>Our method introduces an adapted training scheme that progressively increases the sequence length.<n>By leveraging the recurrent architecture, the model maintains a constant number of parameters regardless of sequence length.
  arXiv  Detail & Related papers  (2025-05-08T07:52:37Z)
• EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling [8.250616459360684]
  We introduce EDELINE, a unified world model architecture that integrates state space models with diffusion models.<n>Our approach outperforms existing baselines across visually challenging Atari 100k tasks, memory-demanding benchmark, and 3D first-person ViZDoom environments.
  arXiv  Detail & Related papers  (2025-02-01T15:49:59Z)
• Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging [75.93960998357812]
  Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their capabilities across different tasks and domains.<n>Current model merging techniques focus on merging all available models simultaneously, with weight matrices-based methods being the predominant approaches.<n>We propose a training-free projection-based continual merging method that processes models sequentially.
  arXiv  Detail & Related papers  (2025-01-16T13:17:24Z)
• State Soup: In-Context Skill Learning, Retrieval and Mixing [22.485700977542127]
  A new breed of gated-linear recurrent neural networks has reached state-of-the-art performance on a range of sequence modeling problems. Here, we explore another advantage of these stateful sequence models, inspired by the success of model merging through parameter. Building on parallels between fine-tuning and in-context learning, we investigate whether we can treat internal states as task vectors that can be stored, retrieved, and then linearly combined.
  arXiv  Detail & Related papers  (2024-06-12T17:06:07Z)
• Gated Recurrent Neural Networks with Weighted Time-Delay Feedback [55.596897987498174]
  We present a novel approach to modeling long-term dependencies in sequential data by introducing a gated recurrent unit (GRU) with a weighted time-delay feedback mechanism.<n>Our proposed model, named $tau$-GRU, is a discretized version of a continuous-time formulation of a recurrent unit, where the dynamics are governed by delay differential equations (DDEs)
  arXiv  Detail & Related papers  (2022-12-01T02:26:34Z)
• Deep Explicit Duration Switching Models for Time Series [84.33678003781908]
  We propose a flexible model that is capable of identifying both state- and time-dependent switching dynamics. State-dependent switching is enabled by a recurrent state-to-switch connection. An explicit duration count variable is used to improve the time-dependent switching behavior.
  arXiv  Detail & Related papers  (2021-10-26T17:35:21Z)

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.