@inproceedings{bania-etal-2026-lrnnx,
title = "lrnnx: A library for Linear {RNN}s",
author = "Bania, Karan and
Kalburgi, Soham and
Tanwar, Manit and
Dhruthi and
Nagarsekar, Aditya and
Mestha, Harshvardhan and
Chibber, Naman and
Deshmukh, Raj and
Sathyanarayanan, Anish and
Rathore, Aarush and
Chheda, Pratham",
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.60/",
pages = "811--817",
ISBN = "979-8-89176-383-8",
abstract = "Linear recurrent neural networks (LRNNs) provide a structured approach to sequence modeling that bridges classical linear dynamical systems and modern deep learning, offering both expressive power and theoretical guarantees on stability and trainability. In recent years, multiple LRNN-based architectures have been proposed, each introducing distinct parameterizations, discretization schemes, and implementation constraints. However, existing implementations are fragmented across different software frameworks, often rely on framework-specific optimizations, and in some cases require custom CUDA kernels or lack publicly available code altogether. As a result, using, comparing, or extending LRNNs requires substantial implementation effort. To address this, we introduce $\texttt{lrnnx}$, a unified software library that implements several modern LRNN architectures under a common interface. The library exposes multiple levels of control, allowing users to work directly with core components or higher-level model abstractions. $\texttt{lrnnx}$ aims to improve accessibility, reproducibility, and extensibility of LRNN research and applications. We make our code available under a permissive MIT license."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bania-etal-2026-lrnnx">
<titleInfo>
<title>lrnnx: A library for Linear RNNs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karan</namePart>
<namePart type="family">Bania</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soham</namePart>
<namePart type="family">Kalburgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manit</namePart>
<namePart type="family">Tanwar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Dhruthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Nagarsekar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harshvardhan</namePart>
<namePart type="family">Mestha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naman</namePart>
<namePart type="family">Chibber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Deshmukh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anish</namePart>
<namePart type="family">Sathyanarayanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aarush</namePart>
<namePart type="family">Rathore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pratham</namePart>
<namePart type="family">Chheda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>Linear recurrent neural networks (LRNNs) provide a structured approach to sequence modeling that bridges classical linear dynamical systems and modern deep learning, offering both expressive power and theoretical guarantees on stability and trainability. In recent years, multiple LRNN-based architectures have been proposed, each introducing distinct parameterizations, discretization schemes, and implementation constraints. However, existing implementations are fragmented across different software frameworks, often rely on framework-specific optimizations, and in some cases require custom CUDA kernels or lack publicly available code altogether. As a result, using, comparing, or extending LRNNs requires substantial implementation effort. To address this, we introduce lrnnx, a unified software library that implements several modern LRNN architectures under a common interface. The library exposes multiple levels of control, allowing users to work directly with core components or higher-level model abstractions. lrnnx aims to improve accessibility, reproducibility, and extensibility of LRNN research and applications. We make our code available under a permissive MIT license.</abstract>
<identifier type="citekey">bania-etal-2026-lrnnx</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.60/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>811</start>
<end>817</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T lrnnx: A library for Linear RNNs
%A Bania, Karan
%A Kalburgi, Soham
%A Tanwar, Manit
%A Nagarsekar, Aditya
%A Mestha, Harshvardhan
%A Chibber, Naman
%A Deshmukh, Raj
%A Sathyanarayanan, Anish
%A Rathore, Aarush
%A Chheda, Pratham
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%A Dhruthi
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F bania-etal-2026-lrnnx
%X Linear recurrent neural networks (LRNNs) provide a structured approach to sequence modeling that bridges classical linear dynamical systems and modern deep learning, offering both expressive power and theoretical guarantees on stability and trainability. In recent years, multiple LRNN-based architectures have been proposed, each introducing distinct parameterizations, discretization schemes, and implementation constraints. However, existing implementations are fragmented across different software frameworks, often rely on framework-specific optimizations, and in some cases require custom CUDA kernels or lack publicly available code altogether. As a result, using, comparing, or extending LRNNs requires substantial implementation effort. To address this, we introduce lrnnx, a unified software library that implements several modern LRNN architectures under a common interface. The library exposes multiple levels of control, allowing users to work directly with core components or higher-level model abstractions. lrnnx aims to improve accessibility, reproducibility, and extensibility of LRNN research and applications. We make our code available under a permissive MIT license.
%U https://aclanthology.org/2026.eacl-srw.60/
%P 811-817
Markdown (Informal)
[lrnnx: A library for Linear RNNs](https://aclanthology.org/2026.eacl-srw.60/) (Bania et al., EACL 2026)
ACL
- Karan Bania, Soham Kalburgi, Manit Tanwar, Dhruthi, Aditya Nagarsekar, Harshvardhan Mestha, Naman Chibber, Raj Deshmukh, Anish Sathyanarayanan, Aarush Rathore, and Pratham Chheda. 2026. lrnnx: A library for Linear RNNs. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 811–817, Rabat, Morocco. Association for Computational Linguistics.