{"id":"https://openalex.org/W7138053366","doi":"https://doi.org/10.1609/aaai.v40i2.37136","title":"TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks","display_name":"TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138053366","doi":"https://doi.org/10.1609/aaai.v40i2.37136"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i2.37136","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37136","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i2.37136","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104174550","display_name":"Xuanle Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanle Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129674662","display_name":"Shuxin Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuxin Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129707114","display_name":"Xinyuan Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyuan Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129673391","display_name":"Xiang Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129740029","display_name":"Duzhen Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duzhen Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009070585","display_name":"Xiuyi Chen","orcid":"https://orcid.org/0000-0002-9351-4160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiuyi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129741352","display_name":"Bo Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"2","first_page":"1596","last_page":"1604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.8671000003814697,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.8671000003814697,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.030899999663233757,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0215000007301569,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5932999849319458},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5375999808311462},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5360000133514404},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4885999858379364},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4494999945163727},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.39430001378059387},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3652999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593500018119812},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5932999849319458},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48739999532699585},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C94361409","wikidata":"https://www.wikidata.org/wiki/Q7882500","display_name":"Uncertainty reduction theory","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i2.37136","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37136","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37136","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i2.37136","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i2.37136","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5899925827980042,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Vision":[1],"Language":[2],"Models":[3],"(VLMs)":[4],"have":[5],"demonstrated":[6],"remarkable":[7],"capabilities":[8],"in":[9,15,75],"general":[10],"visual":[11,33,92,182],"understanding,":[12],"their":[13],"application":[14],"the":[16,181],"chemical":[17,47,60,76,88,192],"domain":[18],"has":[19],"been":[20],"limited,":[21],"with":[22,62,146],"previous":[23],"works":[24],"predominantly":[25],"focusing":[26],"on":[27,69,154],"text":[28],"and":[29,86,95,102,117,139,157,165,198],"thus":[30],"overlooking":[31],"critical":[32],"information,":[34],"such":[35],"as":[36,131],"molecular":[37,125,156],"structures.":[38],"Current":[39],"approaches":[40],"that":[41,72,90],"directly":[42],"adopt":[43],"standard":[44],"VLMs":[45,190],"for":[46,112,191],"tasks":[48,71,97],"suffer":[49],"from":[50,124],"two":[51],"primary":[52],"issues:":[53],"(i)":[54],"computational":[55],"inefficiency":[56],"of":[57,180],"processing":[58],"entire":[59],"images":[61,126],"non-informative":[63],"backgrounds.":[64],"(ii)":[65],"a":[66,109,128],"narrow":[67],"scope":[68],"molecular-level":[70],"restricts":[73],"progress":[74],"reasoning.":[77],"In":[78],"this":[79],"work,":[80],"we":[81,106],"propose":[82,107],"TinyChemVL,":[83],"an":[84],"efficient":[85,187],"powerful":[87,189],"VLM":[89],"leverages":[91],"token":[93],"reduction":[94],"reaction-level":[96,110],"to":[98,135,169],"improve":[99],"model":[100,196],"efficiency":[101],"reasoning":[103,140],"capacity.":[104],"Also,":[105],"ChemRxn-V,":[108],"benchmark":[111],"assessing":[113],"vision-based":[114],"reaction":[115,122,158],"recognition":[116,138],"prediction":[118],"tasks.":[119],"Directly":[120],"predicting":[121],"products":[123],"poses":[127],"non-trivial":[129],"challenge,":[130],"it":[132],"requires":[133],"models":[134],"integrate":[136],"both":[137,155],"capacities.":[141],"Our":[142],"results":[143],"demonstrate":[144],"that,":[145],"only":[147,178],"4B":[148],"parameters,":[149],"TinyChemVL":[150,173],"achieves":[151],"superior":[152],"performance":[153],"tasks,":[159],"while":[160,176],"also":[161],"demonstrating":[162],"faster":[163],"inference":[164],"training":[166],"speeds":[167],"compared":[168],"existing":[170],"models.":[171],"Notably,":[172],"outperforms":[174],"ChemVLM":[175],"utilizing":[177],"1/16th":[179],"tokens.":[183],"This":[184],"work":[185],"builds":[186],"yet":[188],"domains":[193],"by":[194],"co-designing":[195],"architecture":[197],"task":[199],"complexity.":[200]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}