{"ID":2888243,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.23292","arxiv_id":"2507.23292","title":"SequenceLayers: Sequence Processing and Streaming Neural Networks Made Easy","abstract":"We introduce a neural network layer API and library for sequence modeling, designed for easy creation of sequence models that can be executed both layer-by-layer (e.g., teacher-forced training) and step-by-step (e.g., autoregressive sampling). To achieve this, layers define an explicit representation of their state over time (e.g., a Transformer KV cache, a convolution buffer, an RNN hidden state), and a step method that evolves that state, tested to give identical results to a stateless layer-wise invocation. This and other aspects of the SequenceLayers contract enables complex models to be immediately streamable, mitigates a wide range of common bugs arising in both streaming and parallel sequence processing, and can be implemented in any deep learning library. A composable and declarative API, along with a comprehensive suite of layers and combinators, streamlines the construction of production-scale models from simple streamable components while preserving strong correctness guarantees. Our current implementations of SequenceLayers (JAX, TensorFlow 2) are available at https://github.com/google/sequence-layers.","short_abstract":"We introduce a neural network layer API and library for sequence modeling, designed for easy creation of sequence models that can be executed both layer-by-layer (e.g., teacher-forced training) and step-by-step (e.g., autoregressive sampling). To achieve this, layers define an explicit representation of their state ove...","url_abs":"https://arxiv.org/abs/2507.23292","url_pdf":"https://arxiv.org/pdf/2507.23292v1","authors":"[\"RJ Skerry-Ryan\",\"Julian Salazar\",\"Soroosh Mariooryad\",\"David Kao\",\"Daisy Stanton\",\"Eric Battenberg\",\"Matt Shannon\",\"Ron J. Weiss\",\"Robin Scheibler\",\"Jonas Rothfuss\",\"Tom Bagby\"]","published":"2025-07-31T07:10:39Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CL\",\"cs.PL\",\"cs.SE\",\"eess.AS\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":611518,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2888243,"paper_url":"https://arxiv.org/abs/2507.23292","paper_title":"SequenceLayers: Sequence Processing and Streaming Neural Networks Made Easy","repo_url":"https://github.com/google/sequence-layers","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}