{"id":"https://openalex.org/W7163023595","doi":"https://doi.org/10.48550/arxiv.2605.30794","title":"MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding","display_name":"MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163023595","doi":"https://doi.org/10.48550/arxiv.2605.30794"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.30794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.30794","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137527151","display_name":"Qian Kou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kou, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137576419","display_name":"Xiaofeng Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Xiaofeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137564342","display_name":"Yulin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yulin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137583774","display_name":"Xiaosong Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Xiaosong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137520535","display_name":"Xinyang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xinyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124888193","display_name":"Hua Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Hua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076460871","display_name":"\u66f9\u4e1c\u5174 Cao Dongxing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongxing, Cao","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9746000170707703,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9746000170707703,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.005499999970197678,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.003100000089034438,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/relation","display_name":"Relation (database)","score":0.5726000070571899},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5629000067710876},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.49950000643730164},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4982999861240387},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4781999886035919},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.42320001125335693},{"id":"https://openalex.org/keywords/technical-drawing","display_name":"Technical drawing","score":0.4133000075817108},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.37770000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5737000107765198},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5726000070571899},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5629000067710876},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C145961650","wikidata":"https://www.wikidata.org/wiki/Q192521","display_name":"Technical drawing","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39989998936653137},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39579999446868896},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C3019308078","wikidata":"https://www.wikidata.org/wiki/Q229367","display_name":"3d printed","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3149000108242035},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.30794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.30794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"demonstrated":[6],"significant":[7],"achievements":[8],"in":[9,168],"general":[10],"visual":[11],"question":[12],"answering":[13],"(VQA)":[14],"tasks.":[15],"However,":[16],"they":[17],"remain":[18],"brittle":[19],"on":[20,110,149],"mechanical":[21,66,112,156,169],"engineering":[22],"drawings,":[23],"where":[24],"high":[25],"annotation":[26],"density":[27],"and":[28,42,51,76,99,106,160,171],"weak":[29],"domain":[30],"knowledge,":[31],"compounded":[32],"by":[33,145],"unreliable":[34],"spatial":[35],"relation":[36],"reasoning":[37],"under":[38],"strict":[39],"projection":[40],"rules":[41],"geometric":[43],"constraints,":[44],"make":[45],"decisive":[46],"cues":[47],"easy":[48],"to":[49,54,104],"miss":[50],"frequently":[52],"lead":[53],"wrong":[55],"answers.":[56],"To":[57],"bridge":[58],"this":[59],"gap,":[60],"we":[61,118],"introduce":[62],"the":[63,121,141,150],"first":[64],"comprehensive":[65],"drawing":[67,157],"understanding":[68,109,158],"dataset,":[69],"MechVQA,":[70,117],"created":[71],"through":[72,124],"a":[73,102,125,130,162],"semi-automated":[74],"construction":[75],"quality-control":[77],"pipeline.":[78],"MechVQA":[79,151],"contains":[80],"3.3k":[81],"high-density":[82],"pictures":[83],"with":[84],"21K":[85],"question-answer":[86],"pairs,":[87],"spanning":[88],"10":[89],"different":[90],"fine-grained":[91],"tasks":[92],"across":[93],"three":[94],"capability":[95],"levels:":[96],"Recognition,":[97],"Reasoning,":[98],"Judging,":[100],"providing":[101,161],"testbed":[103],"evaluate":[105],"improve":[107],"MLLM":[108],"real-world":[111],"drawings.":[113],"On":[114],"top":[115],"of":[116],"then":[119],"develop":[120],"MechVL":[122,139],"model":[123],"multi-stage":[126],"training":[127],"paradigm,":[128],"building":[129],"strong":[131],"domain-specialized":[132],"baseline.":[133],"Extensive":[134],"experimental":[135],"results":[136],"demonstrate":[137],"that":[138],"outperforms":[140],"strongest":[142],"closed-source":[143],"baseline":[144],"7.57":[146],"percentage":[147],"points":[148],"total":[152],"score,":[153],"significantly":[154],"enhancing":[155],"ability":[159],"reusable":[163],"foundation":[164],"for":[165],"deploying":[166],"MLLMs":[167],"design":[170],"inspection":[172],"scenarios.":[173]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-02T00:00:00"}