{"id":"https://openalex.org/W4414359290","doi":"https://doi.org/10.24963/ijcai.2025/1023","title":"Unified Molecule-Text Language Model with Discrete Token Representation","display_name":"Unified Molecule-Text Language Model with Discrete Token Representation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359290","doi":"https://doi.org/10.24963/ijcai.2025/1023"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1023","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033380004","display_name":"Shuhan Guo","orcid":"https://orcid.org/0009-0003-0389-445X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhan Guo","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045777220","display_name":"Yatao Bian","orcid":"https://orcid.org/0000-0002-2368-4084"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yatao Bian","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027416136","display_name":"Ruibing Wang","orcid":"https://orcid.org/0000-0001-9489-4241"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibing Wang","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112114244","display_name":"Nan Yin","orcid":"https://orcid.org/0000-0002-9792-6066"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nan Yin","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422246","display_name":"Zhen Wang","orcid":"https://orcid.org/0000-0001-5007-6327"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072484211","display_name":"Quanming Yao","orcid":"https://orcid.org/0000-0001-8944-8618"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quanming Yao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19459381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9205","last_page":"9213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9646999835968018,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9646999835968018,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.9351999759674072,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6783000230789185},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5914000272750854},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.48809999227523804},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.47940000891685486},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.45980000495910645},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4510999917984009},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44269999861717224},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4147999882698059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898999810218811},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6783000230789185},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5914000272750854},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47690001130104065},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47279998660087585},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3174999952316284},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1023","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"remarkable":[1],"success":[2],"of":[3,67,99,164,183],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"across":[8,179],"diverse":[9],"tasks":[10],"has":[11],"driven":[12],"the":[13,45,65,85,135],"research":[14],"community":[15],"to":[16,20,32,83,137],"extend":[17],"their":[18],"capabilities":[19],"molecular":[21,25,46,95,108,139],"applications.":[22],"However,":[23],"most":[24],"LLMs":[26,68],"employ":[27],"adapter-based":[28],"architectures":[29],"that":[30,63,79,174],"fail":[31],"equally":[33],"integrate":[34],"molecule":[35,70,89,119,184],"and":[36,39,90,110,120,128,146,168,186],"text":[37,121],"modalities":[38,122],"lack":[40],"explicit":[41],"supervision":[42],"signals":[43],"for":[44],"modality.":[47],"To":[48],"address":[49],"these":[50],"issues,":[51],"we":[52,73],"introduce":[53,74],"UniMoT,":[54],"a":[55,60,75,81,124,142,153,160,180],"Unified":[56],"Molecule-Text":[57],"LLM":[58],"adopting":[59],"tokenizer-based":[61],"architecture":[62],"expands":[64],"vocabulary":[66],"with":[69,114],"tokens.":[71],"Specifically,":[72],"Vector":[76],"Quantization-driven":[77],"tokenizer":[78,93],"incorporates":[80],"Q-Former":[82],"bridge":[84],"modality":[86],"gap":[87],"between":[88],"text.":[91],"This":[92,133],"transforms":[94],"structures":[96,140],"into":[97],"sequences":[98],"tokens":[100],"exhibiting":[101],"causal":[102],"dependency,":[103],"thereby":[104],"encapsulating":[105],"both":[106,166],"high-level":[107],"features":[109],"textual":[111,150],"information.":[112],"Equipped":[113],"this":[115],"tokenizer,":[116],"UniMoT":[117,157,175],"unifies":[118],"under":[123],"shared":[125],"token":[126],"representation":[127],"an":[129],"autoregressive":[130],"training":[131,155],"paradigm.":[132],"enables":[134],"model":[136],"process":[138],"as":[141,159],"distinct":[143],"linguistic":[144],"system":[145],"generate":[147],"them":[148],"in":[149],"form.":[151],"Through":[152],"four-stage":[154],"scheme,":[156],"functions":[158],"multi-modal":[161],"generalist":[162],"capable":[163],"performing":[165],"molecule-to-text":[167],"text-to-molecule":[169],"tasks.":[170,188],"Extensive":[171],"experiments":[172],"demonstrate":[173],"achieves":[176],"state-of-the-art":[177],"performance":[178],"wide":[181],"range":[182],"comprehension":[185],"generation":[187]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}