{"id":"https://openalex.org/W7163702967","doi":"https://doi.org/10.48550/arxiv.2606.05445","title":"Brick-Composer: Using MLLMs for Assembly with Diverse Bricks","display_name":"Brick-Composer: Using MLLMs for Assembly with Diverse Bricks","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163702967","doi":"https://doi.org/10.48550/arxiv.2606.05445"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.05445","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05445","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"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.2606.05445","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137941584","display_name":"Jiateng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiateng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137933275","display_name":"Bingxuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bingxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137938703","display_name":"Zhenhailong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhenhailong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038652158","display_name":"Rushi Wang","orcid":"https://orcid.org/0000-0001-9366-9288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Rushi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070225549","display_name":"Kaiwen Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Kaiwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137956735","display_name":"Cheng Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137946308","display_name":"Jiayu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiayu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137945582","display_name":"Denghui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Denghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137928792","display_name":"Katherine Driggs-Campbell","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Driggs-Campbell, Katherine","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137969544","display_name":"Manling Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Manling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137962470","display_name":"Heng Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Heng","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":0.27129998803138733,"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":0.27129998803138733,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.24310000240802765,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05090000107884407,"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/brick","display_name":"Brick","score":0.8234999775886536},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.633400022983551},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.609499990940094},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5249999761581421},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5138999819755554},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47510001063346863}],"concepts":[{"id":"https://openalex.org/C154226666","wikidata":"https://www.wikidata.org/wiki/Q40089","display_name":"Brick","level":2,"score":0.8234999775886536},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.633400022983551},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.609499990940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5320000052452087},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3928000032901764},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3345000147819519},{"id":"https://openalex.org/C165062768","wikidata":"https://www.wikidata.org/wiki/Q1145644","display_name":"Biomimetics","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31520000100135803},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C2777315864","wikidata":"https://www.wikidata.org/wiki/Q15853013","display_name":"Visual Basic","level":3,"score":0.266400009393692}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.05445","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05445","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.05445","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05445","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.4095322787761688,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,45],"dream":[1],"of":[2,212],"AI":[3],"agents":[4],"that":[5,106,136,220],"can":[6,206,222],"read":[7],"arbitrary":[8],"designs":[9],"and":[10,37,69,75,120,162,165,189],"construct":[11],"real-world":[12],"objects":[13],"from":[14,66,112,195],"reusable":[15],"building":[16],"blocks.":[17],"As":[18],"a":[19,50,133,204,216],"first":[20,94],"step":[21,56],"toward":[22],"this":[23,85,128],"vision,":[24],"we":[25,87,130],"study":[26],"whether":[27],"multimodal":[28],"large":[29],"language":[30],"models":[31],"(MLLMs)":[32],"possess":[33],"the":[34,63,77,93,213],"visual":[35,161],"grounding":[36],"spatial":[38],"reasoning":[39],"capabilities":[40,225],"required":[41],"for":[42,96,215],"brick":[43,47,60,65,70,79,118,177],"assembly.":[44],"formulate":[46],"assembly":[48,100,140,193,224],"as":[49],"sequential":[51],"decision-making":[52],"problem,":[53],"where":[54,74],"each":[55],"involves":[57],"two":[58],"subtasks:":[59],"selection,":[61],"identifying":[62],"target":[64],"candidate":[67],"components,":[68],"pose":[71,124,186],"estimation,":[72],"predicting":[73],"how":[76],"selected":[78],"should":[80],"be":[81],"placed.":[82],"To":[83,126],"support":[84],"study,":[86],"introduce":[88],"BC-Bench":[89],"(Brick":[90],"Construction":[91],"Benchmark),":[92],"benchmark":[95],"evaluating":[97],"MLLMs":[98,109,138,221],"on":[99],"with":[101,116,139],"diverse":[102],"bricks.":[103],"Experiments":[104],"show":[105],"current":[107],"state-of-the-art":[108],"remain":[110],"far":[111],"reliable":[113],"builders,":[114],"struggling":[115],"fine-grained":[117],"selection":[119,178],"failing":[121],"at":[122],"precise":[123],"estimation.":[125],"bridge":[127],"gap,":[129],"propose":[131],"Brick-Composer,":[132],"learning":[134,170],"framework":[135],"equips":[137],"skills":[141],"through":[142,226],"three":[143,182],"complementary":[144],"signals:":[145],"Human":[146],"Design":[147],"Sparks,":[148],"which":[149,156,168],"provide":[150],"affordance-rich":[151],"construction":[152],"demonstrations;":[153],"World":[154],"Feedback,":[155],"grounds":[157],"predicted":[158],"actions":[159],"in":[160],"physical":[163],"consequences;":[164],"Synthetic":[166],"Experience,":[167],"scales":[169],"beyond":[171],"existing":[172],"object":[173],"designs.":[174],"Brick-Composer":[175],"improves":[176],"accuracy":[179],"by":[180],"over":[181],"times,":[183],"substantially":[184],"reduces":[185],"estimation":[187],"errors,":[188],"raises":[190],"strict":[191],"step-level":[192],"success":[194],"less":[196],"than":[197],"1%":[198],"to":[199,210],"around":[200],"15%.":[201],"After":[202],"training,":[203],"Qwen-3-8B":[205],"correctly":[207],"compose":[208],"up":[209],"42%":[211],"steps":[214],"complete":[217],"object,":[218],"suggesting":[219],"acquire":[223],"targeted,":[227],"physically":[228],"grounded":[229],"learning.":[230]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-06T00:00:00"}