{"id":"https://openalex.org/W4403818863","doi":"https://doi.org/10.1109/iccv51701.2025.00372","title":"Robin3D Improving 3D Large Language Model via Robust Instruction Tuning","display_name":"Robin3D Improving 3D Large Language Model via Robust Instruction Tuning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4403818863","doi":"https://doi.org/10.1109/iccv51701.2025.00372"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.00255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114426745","display_name":"Weitai Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weitai Kang","raw_affiliation_strings":["University of Illinois Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055142075","display_name":"Haifeng Huang","orcid":"https://orcid.org/0000-0002-1615-3779"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Huang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuzhang Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzhang Shang","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080823547","display_name":"Mubarak Shah","orcid":"https://orcid.org/0000-0001-6172-5572"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mubarak Shah","raw_affiliation_strings":["University of Central Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100395068","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0002-5917-1475"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["University of Illinois Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114426745"],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00060828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3905","last_page":"3915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9714999794960022,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9714999794960022,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9323999881744385,"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":0.9319999814033508,"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/computer-science","display_name":"Computer science","score":0.6479050517082214},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44616642594337463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24986669421195984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6479050517082214},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44616642594337463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24986669421195984}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.00255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.00255","pdf_url":"https://arxiv.org/pdf/2410.00255","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.00255","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.00255","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.00255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.00255","pdf_url":"https://arxiv.org/pdf/2410.00255","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5388791790","display_name":null,"funder_award_id":"IIS-2525840,CNS-2432534,ECCS-2514574","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8239671734","display_name":null,"funder_award_id":"1RF1MH133764-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403818863.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,12,16,179,188],"3D":[3,18,163],"Large":[4],"Language":[5],"Models":[6],"(3DLLMs)":[7],"have":[8],"highlighted":[9],"their":[10],"potential":[11],"building":[13],"general-purpose":[14],"agents":[15],"the":[17,26,74,87,92,146,168,180,189],"real":[19],"world,":[20],"yet":[21],"challenges":[22],"remain":[23],"due":[24],"to":[25,34,85,101,139],"lack":[27],"of":[28,40,115],"high-quality":[29],"robust":[30],"instruction-following":[31,54,112],"data,":[32,77,95,113],"leading":[33],"limited":[35],"discriminative":[36,89],"power":[37],"and":[38,82,122,143,149,184],"generalization":[39],"3DLLMs.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,108,174],"introduce":[46],"Robin3D,":[47],"a":[48,106,176,185],"powerful":[49],"3DLLM":[50],"trained":[51],"on":[52],"large-scale":[53],"data":[55,60],"generated":[56],"by":[57],"our":[58],"novel":[59],"engine,":[61],"Robust":[62],"Instruction":[63],"Generation":[64],"(RIG)":[65],"engine.":[66],"RIG":[67],"generates":[68],"two":[69],"key":[70],"instruction":[71,99],"data:":[72],"1)":[73],"Adversarial":[75,117],"Instruction-following":[76,94],"which":[78,96],"features":[79],"mixed":[80],"negative":[81],"positive":[83],"samples":[84],"enhance":[86,102,140],"model's":[88,103],"understanding.":[90],"2)":[91],"Diverse":[93,120],"contains":[97],"various":[98],"styles":[100],"generalization.":[104],"As":[105],"result,":[107],"construct":[109],"1":[110],"million":[111],"consisting":[114],"344K":[116],"samples,":[118,121],"508K":[119],"165K":[123],"benchmark":[124],"training":[125],"set":[126],"samples.":[127],"To":[128],"better":[129],"handle":[130],"these":[131],"complex":[132],"instructions,":[133],"Robin3D":[134,155],"first":[135],"incorporates":[136],"Relation-Augmented":[137],"Projector":[138],"spatial":[141],"understanding,":[142],"then":[144],"strengthens":[145],"object":[147],"referring":[148],"grounding":[150,181],"ability":[151],"through":[152],"ID-Feature":[153],"Bonding.":[154],"consistently":[156],"outperforms":[157],"previous":[158],"methods":[159],"across":[160],"five":[161],"widely-used":[162],"multimodal":[164],"learning":[165],"benchmarks,":[166],"without":[167],"need":[169],"for":[170],"task-specific":[171],"fine-tuning.":[172],"Notably,":[173],"achieve":[175],"7.8\\%":[177],"improvement":[178,187],"task":[182,191],"(Multi3DRefer)":[183],"6.9\\%":[186],"captioning":[190],"(Scan2Cap).":[192]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}