<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04760148</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-25T04:39:51+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Advancing materials science through next-generation machine learning</title>
            <author role="aut">
              <persName>
                <forename type="first">Rohit</forename>
                <surname>Unni</surname>
              </persName>
              <idno type="halauthorid">3280761-0</idno>
              <affiliation ref="#struct-74980"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mingyuan</forename>
                <surname>Zhou</surname>
              </persName>
              <idno type="halauthorid">3280762-0</idno>
              <affiliation ref="#struct-74980"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Peter</forename>
                <surname>Wiecha</surname>
              </persName>
              <email type="md5">e79e35e3623e29c452705c325f364f96</email>
              <email type="domain">laas.fr</email>
              <idno type="idhal" notation="string">peter-wiecha</idno>
              <idno type="idhal" notation="numeric">20601</idno>
              <idno type="halauthorid" notation="string">48664-20601</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4571-0116</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.de/citations?user=2iMbkAsAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/203873327</idno>
              <affiliation ref="#struct-390153"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Yuebing</forename>
                <surname>Zheng</surname>
              </persName>
              <idno type="halauthorid">2182331-0</idno>
              <affiliation ref="#struct-74980"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Peter</forename>
                <surname>Wiecha</surname>
              </persName>
              <email type="md5">e79e35e3623e29c452705c325f364f96</email>
              <email type="domain">laas.fr</email>
            </editor>
            <funder ref="#projanr-66312"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-10-30 12:10:35</date>
              <date type="whenModified">2025-10-22 18:04:09</date>
              <date type="whenReleased">2024-11-05 16:50:57</date>
              <date type="whenProduced">2024-06</date>
              <date type="whenEndEmbargoed">2024-10-30</date>
              <ref type="file" target="https://laas.hal.science/hal-04760148v1/document">
                <date notBefore="2024-10-30"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://laas.hal.science/hal-04760148v1/file/perspective_COSSMS_final.pdf" id="file-4760148-4145354">
                <date notBefore="2024-10-30"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="643654">
                <persName>
                  <forename>Peter</forename>
                  <surname>Wiecha</surname>
                </persName>
                <email type="md5">e79e35e3623e29c452705c325f364f96</email>
                <email type="domain">laas.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04760148</idno>
            <idno type="halUri">https://laas.hal.science/hal-04760148</idno>
            <idno type="halBibtex">unni:hal-04760148</idno>
            <idno type="halRefHtml">&lt;i&gt;Current Opinion in Solid State and Materials Science&lt;/i&gt;, 2024, 30, pp.101157. &lt;a target="_blank" href="https://dx.doi.org/10.1016/j.cossms.2024.101157"&gt;&amp;#x27E8;10.1016/j.cossms.2024.101157&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Current Opinion in Solid State and Materials Science, 2024, 30, pp.101157. &amp;#x27E8;10.1016/j.cossms.2024.101157&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4760148-4145354"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-TLSE2">Université Toulouse 2</idno>
            <idno type="stamp" n="UNIV-TLSE3">Université de Toulouse</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INSA-TOULOUSE">Institut National des Sciences Appliquées de Toulouse</idno>
            <idno type="stamp" n="LAAS">Laboratoire d'analyse et d'architecture des systèmes</idno>
            <idno type="stamp" n="UT1-CAPITOLE">Université Toulouse 1 Capitole</idno>
            <idno type="stamp" n="LAAS-MPN" corresp="LAAS-MICRO-NANO-BIO-TECHNOLOGIES">Équipe Matériaux et Procédés pour la Nanoélectronique</idno>
            <idno type="stamp" n="LAAS-MICRO-NANO-BIO-TECHNOLOGIES" corresp="LAAS">LAAS-Micro Nano Bio Technologies</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="TOULOUSE-INP">Toulouse - INP</idno>
            <idno type="stamp" n="UNIV-UT3">Université Toulouse 3</idno>
            <idno type="stamp" n="UT3-INP">Université de Toulouse / Toulouse INP</idno>
            <idno type="stamp" n="UT3-TOULOUSEINP">Université de Toulouse / Toulouse INP</idno>
            <idno type="stamp" n="TEST7-HALCNRS">test 7 du portail hal cnrs</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Advancing materials science through next-generation machine learning</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Rohit</forename>
                    <surname>Unni</surname>
                  </persName>
                  <idno type="halauthorid">3280761-0</idno>
                  <affiliation ref="#struct-74980"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mingyuan</forename>
                    <surname>Zhou</surname>
                  </persName>
                  <idno type="halauthorid">3280762-0</idno>
                  <affiliation ref="#struct-74980"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Peter</forename>
                    <surname>Wiecha</surname>
                  </persName>
                  <email type="md5">e79e35e3623e29c452705c325f364f96</email>
                  <email type="domain">laas.fr</email>
                  <idno type="idhal" notation="string">peter-wiecha</idno>
                  <idno type="idhal" notation="numeric">20601</idno>
                  <idno type="halauthorid" notation="string">48664-20601</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4571-0116</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.de/citations?user=2iMbkAsAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/203873327</idno>
                  <affiliation ref="#struct-390153"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Yuebing</forename>
                    <surname>Zheng</surname>
                  </persName>
                  <idno type="halauthorid">2182331-0</idno>
                  <affiliation ref="#struct-74980"/>
                </author>
              </analytic>
              <monogr>
                <idno type="localRef">Rapport LAAS n° 24371</idno>
                <idno type="halJournalId" status="VALID">12309</idno>
                <idno type="issn">1359-0286</idno>
                <title level="j">Current Opinion in Solid State and Materials Science</title>
                <imprint>
                  <publisher>Elsevier</publisher>
                  <biblScope unit="volume">30</biblScope>
                  <biblScope unit="pp">101157</biblScope>
                  <date type="datePub">2024-06</date>
                  <date type="dateEpub">2024-04-03</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1016/j.cossms.2024.101157</idno>
              <ref type="publisher">https://www.sciencedirect.com/science/article/pii/S1359028624000238?via%3Dihub</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">deep learning</term>
                <term xml:lang="en">neural networks</term>
                <term xml:lang="en">materials science</term>
                <term xml:lang="en">large language models</term>
              </keywords>
              <classCode scheme="halDomain" n="phys.cond.cm-ms">Physics [physics]/Condensed Matter [cond-mat]/Materials Science [cond-mat.mtrl-sci]</classCode>
              <classCode scheme="halDomain" n="phys.phys.phys-comp-ph">Physics [physics]/Physics [physics]/Computational Physics [physics.comp-ph]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>&lt;div&gt;&lt;p&gt;For over a decade, machine learning (ML) models have been making strides in computer vision and natural language processing (NLP), demonstrating high proficiency in specialized tasks.&lt;/p&gt;&lt;p&gt;The emergence of large-scale language and generative image models, such as ChatGPT and Stable Diffusion, has significantly broadened the accessibility and application scope of these technologies. Traditional predictive models are typically constrained to mapping input data to numerical values or predefined categories, limiting their usefulness beyond their designated tasks.&lt;/p&gt;&lt;p&gt;In contrast, contemporary models employ representation learning and generative modeling, enabling them to extract and encode key insights from a wide variety of data sources and decode them to create novel responses for desired goals. They can interpret queries phrased in natural language to deduce the intended output. In parallel, the application of ML techniques in materials science has advanced considerably, particularly in areas like inverse design, material prediction, and atomic modeling. Despite these advancements, the current models are overly specialized, hindering their potential to supplant established industrial processes. Materials science, therefore, necessitates the creation of a comprehensive, versatile model capable of interpreting humanreadable inputs, intuiting a wide range of possible search directions, and delivering precise solutions. To realize such a model, the field must adopt cutting-edge representation, generative, and foundation model techniques tailored to materials science. A pivotal component in this endeavor is the establishment of an extensive, centralized dataset encompassing a broad spectrum of research topics. This dataset could be assembled by crowdsourcing global research contributions and developing models to extract data from existing literature and represent them in a homogenous format. A massive dataset can be used to train a central model that learns the underlying physics of the target areas, which can then be connected to a variety of specialized downstream tasks.&lt;/p&gt;&lt;p&gt;Ultimately, the envisioned model would empower users to intuitively pose queries for a wide array of desired outcomes. It would facilitate the search for existing data that closely matches the soughtafter solutions and leverage its understanding of physics and material-behavior relationships to innovate new solutions when pre-existing ones fall short.&lt;/p&gt;&lt;/div&gt;</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-74980" status="VALID">
          <idno type="ROR">https://ror.org/00hj54h04</idno>
          <orgName>University of Texas at Austin [Austin]</orgName>
          <desc>
            <address>
              <addrLine>1 University Station Austin, Texas 78712</addrLine>
              <country key="US"/>
            </address>
            <ref type="url">http://www.utexas.edu/</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-390153" status="OLD">
          <orgName>Équipe Matériaux et Procédés pour la Nanoélectronique</orgName>
          <orgName type="acronym">LAAS-MPN</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.laas.fr/public/fr/mpn</ref>
          </desc>
          <listRelation>
            <relation active="#struct-459" type="direct"/>
            <relation active="#struct-81148" type="indirect"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116255" type="indirect"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="indirect"/>
            <relation active="#struct-217752" type="indirect"/>
            <relation name="UPR8001" active="#struct-441569" type="indirect"/>
            <relation active="#struct-448187" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-459" status="OLD">
          <idno type="IdRef">199278792</idno>
          <idno type="ISNI">0000 0001 2188 216X </idno>
          <idno type="RNSR">199517454Y</idno>
          <idno type="ROR">https://ror.org/03vcm6439</idno>
          <orgName>Laboratoire d'analyse et d'architecture des systèmes</orgName>
          <orgName type="acronym">LAAS</orgName>
          <date type="start">1968-01-01</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>7 Av du colonel Roche 31077 TOULOUSE CEDEX 4</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.laas.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-81148" type="direct"/>
            <relation name="443875" active="#struct-443875" type="indirect"/>
            <relation active="#struct-116255" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation active="#struct-443875" type="indirect"/>
            <relation active="#struct-116256" type="direct"/>
            <relation active="#struct-217752" type="direct"/>
            <relation name="UPR8001" active="#struct-441569" type="direct"/>
            <relation active="#struct-448187" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-81148" status="VALID">
          <idno type="IdRef">026404354</idno>
          <idno type="ISNI">0000000121902837</idno>
          <idno type="ROR">https://ror.org/0443n9e75</idno>
          <orgName>Université Toulouse Capitole</orgName>
          <orgName type="acronym">UT Capitole</orgName>
          <date type="start">1970-01-01</date>
          <desc>
            <address>
              <addrLine>2 rue du Doyen-Gabriel-Marty - 31042 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ut-capitole.fr/</ref>
          </desc>
          <listRelation>
            <relation name="443875" active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-443875" status="VALID">
          <idno type="ROR">https://ror.org/017tgbk05</idno>
          <orgName>Communauté d'universités et établissements de Toulouse</orgName>
          <orgName type="acronym">Comue de Toulouse</orgName>
          <desc>
            <address>
              <addrLine>41 Allée Jules Guesde, 31000 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-toulouse.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-116255" status="VALID">
          <idno type="IdRef">026388766</idno>
          <idno type="ISNI">0000 0001 2286 8343</idno>
          <idno type="ROR">https://ror.org/01h8pf755</idno>
          <idno type="Wikidata">Q858979</idno>
          <orgName>Institut National des Sciences Appliquées - Toulouse</orgName>
          <orgName type="acronym">INSA Toulouse</orgName>
          <date type="start">1963-10-21</date>
          <desc>
            <address>
              <addrLine>135, avenue de Rangueil - 31077 Toulouse cedex 4</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-toulouse.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301232" type="direct"/>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-116256" status="VALID">
          <idno type="IdRef">026403994</idno>
          <idno type="ROR">https://ror.org/04ezk3x31</idno>
          <orgName>Université Toulouse - Jean Jaurès</orgName>
          <orgName type="acronym">UT2J</orgName>
          <date type="start">1971-01-01</date>
          <desc>
            <address>
              <addrLine>5 allées Antonio Machado - 31058 Toulouse Cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse2.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-217752" status="OLD">
          <idno type="IdRef">026404672</idno>
          <idno type="ISNI">0000000121617331</idno>
          <idno type="ROR">https://ror.org/02v6kpv12</idno>
          <idno type="Wikidata">Q1273188</idno>
          <orgName>Université Toulouse III - Paul Sabatier</orgName>
          <orgName type="acronym">UT3</orgName>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>118 route de Narbonne - 31062 Toulouse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tlse3.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-448187" status="VALID">
          <idno type="IdRef">026388820</idno>
          <idno type="ISNI">0000000121766169</idno>
          <idno type="ROR">https://ror.org/033p9g875</idno>
          <orgName>Institut National Polytechnique (Toulouse)</orgName>
          <orgName type="acronym">Toulouse INP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inp-toulouse.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-443875" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-66312" status="VALID">
          <idno type="anr">ANR-22-CE24-0002</idno>
          <orgName>NAINOS</orgName>
          <desc>Nano-technologie et intelligence artificial pour une nouvelle génération de stockage d'information optique</desc>
          <date type="start">2022</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>