Structured Recurrent Mixers for Massively Parallelized Sequence Generation

• URL: http://arxiv.org/abs/2605.08696v1
• Date: Sat, 09 May 2026 05:07:55 GMT
• Title: Structured Recurrent Mixers for Massively Parallelized Sequence Generation
• Abstract summary: We introduce the Structured Recurrent Mixer, an architecture that allows for conversion between a sequence parallel representation at train time and a recurrent representation at inference.<n>We show experimentally that this dual representation allows for greater training efficiency, higher input information capacity, and larger inference throughput and length when compared to other linear complexity models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Over the last two decades, language modeling has experienced a shift from predominantly recurrent architectures that process tokens sequentially during training and inference to non-recurrent models that process sequence elements in parallel during training, which results in greater training efficiency and stability at the expense of lower inference throughput. Here we introduce the Structured Recurrent Mixer, an architecture that allows for algebraic conversion between a sequence parallel representation at train time and a recurrent representation at inference, notably without the need for specialized kernels or device-specific memory management. We show experimentally that this dual representation allows for greater training efficiency, higher input information capacity, and larger inference throughput and concurrency when compared to other linear complexity models. We postulate that recurrent models are poorly suited to extended sequence length scaling for information-rich inputs typical of language, but are well suited to scaling in the sample (batch) dimension due to their constant memory per sample. We provide Mojo/MAX inference implementations of SRMs exhibiting 12x the throughput and 170x the concurrency of similarly powerful Transformers inferenced on vLLM, increases characteristic of Pytorch implementations resulting in a 30\% increase in compute-constant GSM8k Pass@k. We conclude by demonstrating that SRMs are effective reinforcement learning training candidates.

Related papers

• Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling [61.28599393707943]
  Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps.<n>We propose a task-shared core scorer and progress-conditioned generation expansions, optimized through generation decomposition and cross-task core alignment.<n> Experiments on two representative UMM architectures demonstrate consistent quality--efficiency improvements across both tasks, retaining 98.03% of dense understanding performance with a 1.93times$ end-to-end inference speedup.
  arXiv  Detail & Related papers  (2026-08-29T14:27:55Z)
• Auto-Regressive Masked Diffusion Models [9.239507801466322]
  Masked diffusion models (MDMs) have emerged as a promising approach for language modeling.<n>They face a performance gap compared to autoregressive models (ARMs) and require more training iterations.<n>We present the Auto-Regressive Masked Diffusion model, which unifies the training efficiency of autoregressive models with the parallel generation capabilities of diffusion-based models.
  arXiv  Detail & Related papers  (2026-01-23T18:42:30Z)
• Parallelizable memory recurrent units [1.3159512679346688]
  We introduce a new family of RNNs, the memory recurrent units (MRUs), that combine the persistent memory capabilities of nonlinear RNNs with the parallelizable computations of SSMs.<n>We show that BMRU achieves good results in tasks with long-term dependencies, and can be combined with state-space models to create hybrid networks that are parallelizable and have transient dynamics as well as persistent memory.
  arXiv  Detail & Related papers  (2026-01-14T14:01:11Z)
• 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)
• Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation [20.117825519637357]
  We introduce Multiverse, a new generative model that enables natively parallel generation.<n>Next, we build a real-world Multiverse reasoning model with co-design curation of data, algorithm, and system.<n>For data creation, we develop Multiverse Curator, an automated LLM-assisted pipeline.<n>We also implement Multiverse Engine to support parallel inference.
  arXiv  Detail & Related papers  (2025-06-11T17:59:23Z)
• 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)
• Hydraulis: Balancing Large Transformer Model Training via Co-designing Parallel Strategies and Data Assignment [25.38589021788461]
  We develop Hydraulis, which jointly optimize the parallel strategies and data assignment.<n> Empirical results demonstrate that Hydraulis outperforms existing systems by 1.32-2.66 times.
  arXiv  Detail & Related papers  (2024-12-10T20:01:53Z)
• UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using Mamba [7.594115034632109]
  We propose UmambaTSF, a novel long-term time series forecasting framework. It integrates multi-scale feature extraction capabilities of U-shaped encoder-decoder multilayer perceptrons (MLP) with Mamba's long sequence representation. UmambaTSF achieves state-of-the-art performance and excellent generality on widely used benchmark datasets.
  arXiv  Detail & Related papers  (2024-10-15T04:56:43Z)
• Retentive Network: A Successor to Transformer for Large Language Models [91.6652200825638]
  We propose Retentive Network (RetNet) as a foundation architecture for large language models. We theoretically derive the connection between recurrence and attention. Experimental results on language modeling show that RetNet achieves favorable scaling results, parallel training, low-cost deployment, and efficient inference.
  arXiv  Detail & Related papers  (2023-07-17T16:40:01Z)
• RWKV: Reinventing RNNs for the Transformer Era [54.716108899349614]
  We propose a novel model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs. We scale our models as large as 14 billion parameters, by far the largest dense RNN ever trained, and find RWKV performs on par with similarly sized Transformers.
  arXiv  Detail & Related papers  (2023-05-22T13:57:41Z)
• FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification [53.55504611255664]
  FormerTime is a hierarchical representation model for improving the classification capacity for the multivariate time series classification task. It exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism.
  arXiv  Detail & Related papers  (2023-02-20T07:46:14Z)
• 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.