<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>1390-6542</journal-id>
<journal-title><![CDATA[Enfoque UTE]]></journal-title>
<abbrev-journal-title><![CDATA[Enfoque UTE]]></abbrev-journal-title>
<issn>1390-6542</issn>
<publisher>
<publisher-name><![CDATA[Universidad UTE]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S1390-65422026000200002</article-id>
<article-id pub-id-type="doi">10.29019/enfoqueute.1204</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[MAMBA: SSM model as alternative to the transformers]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Bestard Columbié]]></surname>
<given-names><![CDATA[Ana Beatriz]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Cruz Morete]]></surname>
<given-names><![CDATA[Daniela Elizabeth]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Soler Jay]]></surname>
<given-names><![CDATA[Lianet]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[López Ramos]]></surname>
<given-names><![CDATA[Dionis]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Universidad de Oriente  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Cuba</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Universidad de Oriente  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Cuba</country>
</aff>
<aff id="Af3">
<institution><![CDATA[,Universidad de Oriente  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Cabo Verde</country>
</aff>
<aff id="Af4">
<institution><![CDATA[,Universidad de Oriente  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Cuba</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>06</month>
<year>2026</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>06</month>
<year>2026</year>
</pub-date>
<volume>17</volume>
<numero>2</numero>
<fpage>8</fpage>
<lpage>17</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://scielo.senescyt.gob.ec/scielo.php?script=sci_arttext&amp;pid=S1390-65422026000200002&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://scielo.senescyt.gob.ec/scielo.php?script=sci_abstract&amp;pid=S1390-65422026000200002&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://scielo.senescyt.gob.ec/scielo.php?script=sci_pdf&amp;pid=S1390-65422026000200002&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract Mamba is a recent State Space Model (SSM) architecture to improve the computational and scalability limitations of transformer-based sequence models. In this review, we synthesize and compare Mamba&#8217;s core design&#8212;interleaved SSM and feed-forward layers with hardware-aware memory management&#8212;to standard Transformers, highlighting its linear complexity and ability to process extremely long contexts. We analyze published benchmarks showing that Mamba outperforms or matches open-source baselines (e.g. Pythia, RWKV) of similar and even twice the size on zero-shot tasks, scales more efficiently on genomic sequences (processing &gt;1 M tokens with only 74 K parameters), and supports variants such as Jamba (MoE extension), Falcon Mamba 7B, Mamba-2 (Structured SSM), and Mamba-4 with further speed or capacity gains. We discuss adaptations to vision (VIM) and dependency parsing (DepMamba), and emerging hybrids (e.g. Bamba, IBM Granite) that fuse SSM efficiency with Transformer accuracy. Finally, we interpret these findings in the context of real-world constraints&#8212;compute cost, energy, and tooling maturity&#8212;outlining where Mamba excels, and hybrid models may be preferable, and which areas require further optimization. Our conclusions suggest that Mamba and its derivatives offer a viable path toward more sustainable, scalable sequence modeling.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[Resumen Mamba es una arquitectura reciente de Modelo de Espacio de Estados (SSM) que supera las limitaciones computacionales y de escalabilidad de los modelos de secuencia basados en Transformadores. En esta revisión examinamos y comparamos el diseño clave de Mamba &#8212;que combina capas de modelo de espacio de estados (SSM) con capas feed-forward y uso optimizado de memoria&#8212; frente a los modelos transformadores estándar, destacando su complejidad lineal y capacidad para procesar contextos extremadamente largos. Analizamos marcos de referencia publicados que muestran que Mamba supera o iguala a referentes de código abierto (ejemplo, Pythia, RWKV) de tamaño similar e incluso del doble en tareas zero-shot, siendo más eficiente en secuencias genómicas (procesando más de 1 millón de tokens con solo 74 mil parámetros) y admite variantes como Jamba (extensión MoE), Falcon Mamba 7B y Mamba-2 (SSM estructurado) con mayores ganancias de velocidad o capacidad. Discutimos adaptaciones para visión (VIM) y análisis de dependencias (DepMamba), y nuevos híbridos (ejemplo, Bamba, IBM Granite) que combinan la eficiencia de los SSM con la precisión de los Transformers. Finalmente, interpretamos estos hallazgos en el contexto de restricciones del mundo real &#8212;costo computacional, energía y madurez de herramientas&#8212;, señalando dónde sobresale Mamba, dónde pueden preferirse modelos híbridos y qué áreas requieren mayor optimización. Nuestras conclusiones sugieren que Mamba y sus derivados ofrecen un camino viable hacia un modelado de secuencias más sostenible y escalable.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[language models]]></kwd>
<kwd lng="en"><![CDATA[hybrid architectures]]></kwd>
<kwd lng="en"><![CDATA[mamba]]></kwd>
<kwd lng="en"><![CDATA[state space models]]></kwd>
<kwd lng="en"><![CDATA[scalability]]></kwd>
<kwd lng="es"><![CDATA[modelos de lenguaje]]></kwd>
<kwd lng="es"><![CDATA[arquitecturas híbridas]]></kwd>
<kwd lng="es"><![CDATA[mamba]]></kwd>
<kwd lng="es"><![CDATA[modelos de espacio de estados]]></kwd>
<kwd lng="es"><![CDATA[escalabilidad]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Vaswani et al]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Gu and T. Dao]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[Mamba: Linear-Time Sequence Modeling with Selective State Spaces&#8221;, in Proceedings of the First Conference on Language Modeling]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lieber]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
<name>
<surname><![CDATA[Lenz]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Cohen]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
</person-group>
<source><![CDATA[Jamba: A Hybrid Transformer-Mamba Language Model]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bick]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Xing]]></surname>
<given-names><![CDATA[E. P.]]></given-names>
</name>
</person-group>
<source><![CDATA[Proceedings of Machine Learning Research, ML Research Press]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Transformers are SSMs: generalized models and efficient algorithms through structured state space duality]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Dao and A. Gu]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
</person-group>
<source><![CDATA[Proceedings of the 41st International Conference on Machine Learning]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Qin et al]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Gu and T. Dao]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[Mamba: Linear-Time Sequence Modeling with Selective State Spaces]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Integrating the Attention Mechanism Into State Space Models]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hrycej]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Bermeitinger]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Handschuh]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[IEEE Swiss Conference on Data Science]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Theoretical Foundations of Deep Selective State-Space Models]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Muca Cirone]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Orvieto]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Walker]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Salvi]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Lyons]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
</person-group>
<source><![CDATA[Adv. Neural Inf. Process. Syst.]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="">
<article-title xml:lang=""><![CDATA[A Comparative Analysis of the Mamba, Transformer, and CNN Architectures for Multi-Label Chest X-Ray Anomaly Detection in the NIH ChestX-Ray14 Dataset]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Yanar et al]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Mamba-360: Survey of state space models as transformer alternative for long sequence modelling: Methods, Applications, and Challenges]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Patro and V. S. Agneeswaran]]></surname>
<given-names><![CDATA[B. N.]]></given-names>
</name>
</person-group>
<source><![CDATA[Eng. Appl. Artif. Intell]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Keung]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Yang]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
<name>
<surname><![CDATA[Mao]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
<name>
<surname><![CDATA[Sun]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[IEEE/ACM International Conference on Automated Software Engineering (ASE)]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Mei]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
<name>
<surname><![CDATA[Mao]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[Proceedings of the 33rd ACM International Conference on Information and Knowledge Management]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bick]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[K. Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Xing]]></surname>
<given-names><![CDATA[E. P.]]></given-names>
</name>
<name>
<surname><![CDATA[Kolter]]></surname>
<given-names><![CDATA[J. Z.]]></given-names>
</name>
</person-group>
<source><![CDATA[dv. Neural Inf. Process. Syst]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhu]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Liao]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
</person-group>
<source><![CDATA[Proceedings of the 41st International Conference on Machine Learning]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B16">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Berroukham]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Housni]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Lahraichi]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[IEEE Congress on Information Science and Technology (CiSt)]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B17">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hedhoud]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Mekhaznia]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Amroune]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[International Conference on Pattern Analysis and Intelligent Systems (PAIS)]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B18">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cho]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Lee]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Kim]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Park]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
</person-group>
<source><![CDATA[IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B19">
<nlm-citation citation-type="">
<article-title xml:lang=""><![CDATA[A Survey on Visual Mamba]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhang et al]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B20">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Li et al]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B21">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Video Transformers: A Survey]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Selva]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Johansen]]></surname>
<given-names><![CDATA[A. S.]]></given-names>
</name>
<name>
<surname><![CDATA[Escalera]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Nasrollahi]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Moeslund]]></surname>
<given-names><![CDATA[T. B.]]></given-names>
</name>
<name>
<surname><![CDATA[Clapés]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[IEEE Trans. Pattern Anal. Mach. Intell]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B22">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Mamba-Stereo: Mamba Regularization for Stereo matching]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Suo]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Miao]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<source><![CDATA[Pattern Recognit]]></source>
<year>2026</year>
</nlm-citation>
</ref>
<ref id="B23">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Schiff]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Kao]]></surname>
<given-names><![CDATA[C.-H.]]></given-names>
</name>
<name>
<surname><![CDATA[Gokaslan]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Dao]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Kuleshov]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
</person-group>
<source><![CDATA[Proc. Mach. Learn. Res]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B24">
<nlm-citation citation-type="">
<article-title xml:lang=""><![CDATA[DSA Mamba: A Model for Advanced Medical Image Classification]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wang et al]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B25">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Transformer vs. Mamba as Skin Cancer Classifier: Preliminary ResultS]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Nikitin and V. Danilov]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
</person-group>
<source><![CDATA[KPI Sci. News]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B26">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Switch-UMamba: Dynamic scanning vision Mamba UNet for medical image segmentation]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Zheng]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Gao]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
</person-group>
<source><![CDATA[Med. Image Anal]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B27">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Shan]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<source><![CDATA[ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B28">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhao and Y. Zhang]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
</person-group>
<source><![CDATA[International Conference on Machine Learning and Computer Application (ICMLCA)]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B29">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[MambaTransDTA: A Hybrid Mamba-Transformer Architecture for Accurate Drug-Target Binding Affinity Prediction]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lou]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Cai]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
<name>
<surname><![CDATA[Siu]]></surname>
<given-names><![CDATA[S. W. I.]]></given-names>
</name>
</person-group>
<source><![CDATA[J. Chem. Inf. Model.]]></source>
<year>2026</year>
</nlm-citation>
</ref>
<ref id="B30">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[TimeMachine: A Time Series is Worth 4 Mambas for Long-Term Forecasting]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ahamed and Q. Cheng]]></surname>
<given-names><![CDATA[M. A.]]></given-names>
</name>
</person-group>
<source><![CDATA[ECAI 2024, IOS Press]]></source>
<year>1695</year>
</nlm-citation>
</ref>
<ref id="B31">
<nlm-citation citation-type="">
<article-title xml:lang=""><![CDATA[Is Mamba effective for time series forecasting?]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wang et al]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B32">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[ST-MambaSync: Complement the power of Mamba and Transformer fusion for less computational cost in spatial&#8211;temporal traffic forecasting]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Shao]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
<name>
<surname><![CDATA[Yao]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Bell]]></surname>
<given-names><![CDATA[M. G. H.]]></given-names>
</name>
<name>
<surname><![CDATA[Gao]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[Inf. Fusion]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B33">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[WOA-STMamba: A spatiotemporal Mamba model enhanced by Whale Optimization for short-term PM2.5 concentration prediction]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Cheng]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhao]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhu]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
</person-group>
<source><![CDATA[J. Environ. Chem. Eng]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B34">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[EdgeNavMamba: Mamba-Optimized Object Detection for Energy-Efficient Edge Devices]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Aalishah]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Navardi]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Mohsenin]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
</person-group>
<source><![CDATA[IEEE Computer Society]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B35">
<nlm-citation citation-type="">
<article-title xml:lang=""><![CDATA[BitNet: 1-bit Pre-training for Large Language Models]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wang et al]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B36">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kojima]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Matsuo]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Iwasawa]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[Proceedings of the 31st International Conference on Computational Linguistics,]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B37">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Jiang]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Han]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Mesgarani]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
</person-group>
<source><![CDATA[ICASSP 2025 - 2025 IEEE International Conference on Acoustics]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B38">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[ConMamba: A Convolution-Augmented Mamba Encoder Model for Efficient End-to-End ASR Systems]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hou]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Gong]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Qian]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B39">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Jiang]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Y. A.]]></given-names>
</name>
<name>
<surname><![CDATA[Nicolas Florea]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Han]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Mesgarani]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
</person-group>
<source><![CDATA[ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B40">
<nlm-citation citation-type="">
<article-title xml:lang=""><![CDATA[MSDM: A Lightweight Multi-Scale Dynamic Mamba for Dynamic Facial Expression Recognition in Smart Classrooms]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liang et al]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B41">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[LTMHN: Learnable TransMamba Hybrid Network for Remote Sensing Image Superresolution]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Jing]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Rong]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
</person-group>
<source><![CDATA[IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B42">
<nlm-citation citation-type="">
<article-title xml:lang=""><![CDATA[Trans-Mamba: The Cross-network of Transformer and Mamba for Traffic Flow Prediction]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liu et al]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
</nlm-citation>
</ref>
<ref id="B43">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Mamba neural operator: Who wins? transformers vs. state-space models for PDEs]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cheng]]></surname>
<given-names><![CDATA[C.-W.]]></given-names>
</name>
<name>
<surname><![CDATA[Huang]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Yang]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Schönlieb]]></surname>
<given-names><![CDATA[C.-B.]]></given-names>
</name>
<name>
<surname><![CDATA[Aviles-Rivero]]></surname>
<given-names><![CDATA[A. I.]]></given-names>
</name>
</person-group>
<source><![CDATA[J. Comput. Phys]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B44">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[A hybrid model based on transformer and Mamba for enhanced sequence modeling]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhu]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Ruan]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
<name>
<surname><![CDATA[Qian]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[Sci. Rep]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B45">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tang]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Sun]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Shen]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
</person-group>
<source><![CDATA[Bi-Mamba: Towards Accurate 1-Bit State Space Models]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B46">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Mamba Models a possible replacement for Transformers?]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Das]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Sen]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Devendiran]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Python Sci. Conf]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B47">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[State Space Models are Strong Text Reranker]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Yan]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Gupta]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Srikumar]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
</person-group>
<source><![CDATA[Proceedings of the 10th Workshop on Representation Learning for NLP (RepL4NLP-2025), V. Adlakha, A. Chronopoulou, X. L. Li, B. P. Majumder, F. Shi, and G. Vernikos, Eds., Albuquerque, NM: Association for Computational Linguistics]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B48">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[On the Expressiveness and Length Generalization of Selective State Space Models on Regular Languages]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Terzic]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Hersche]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Camposampiero]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Hofmann]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Sebastian]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Rahimi]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[Proc. AAAI Conf. Artif. Intell.]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B49">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Azizi]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Kundu]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Sadeghi]]></surname>
<given-names><![CDATA[M. E.]]></given-names>
</name>
<name>
<surname><![CDATA[Pedram]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<source><![CDATA[MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B50">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[A comprehensive survey and taxonomy of mamba: Applications, Challenges, and Future Directions]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Miao]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
<name>
<surname><![CDATA[Jia]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Xie]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Yang]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
</person-group>
<source><![CDATA[Inf. Fusion]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B51">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[A Comprehensive Survey on Mamba: Architectures, Challenges, and Opportunities]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Salam]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Mahmud]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Islam]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Mukta]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Shatabda]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Computer]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B52">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Exploring the Limitations of Mamba in COPY and CoT Reasoning]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ren]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, C. Christodoulopoulos, T. Chakraborty, C. Rose, and V. Peng, Eds., Suzhou, China: Association for Computational Linguistics]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B53">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[The Hidden Attention of Mamba Models]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ali]]></surname>
<given-names><![CDATA[A. A.]]></given-names>
</name>
<name>
<surname><![CDATA[Zimerman]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Wolf]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
</person-group>
<source><![CDATA[Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), W. Che, J. Nabende, E. Shutova, and M. T. Pilehvar, Eds., Vienna, Austria: Association for Computational Linguistics]]></source>
<year>2025</year>
</nlm-citation>
</ref>
<ref id="B54">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[MambaLRP: Explaining Selective State Space Sequence Models]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Rezaei Jafari]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
<name>
<surname><![CDATA[Montavon]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Müller]]></surname>
<given-names><![CDATA[K.-R.]]></given-names>
</name>
<name>
<surname><![CDATA[Eberle]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
</person-group>
<source><![CDATA[Adv. Neural Inf. Process. Syst]]></source>
<year>2024</year>
</nlm-citation>
</ref>
</ref-list>
</back>
</article>
