{"id":"https://openalex.org/W7166666120","doi":"https://doi.org/10.48550/arxiv.2606.29267","title":"Enhancing Part-Level Point Grounding for Any Open-Source MLLMs","display_name":"Enhancing Part-Level Point Grounding for Any Open-Source MLLMs","publication_year":2026,"publication_date":"2026-06-28","ids":{"openalex":"https://openalex.org/W7166666120","doi":"https://doi.org/10.48550/arxiv.2606.29267"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29267","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29267","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.2606.29267","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109029028","display_name":"Jin-Cheng Jhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jhang, Jin-Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014665083","display_name":"Fu-En Wang","orcid":"https://orcid.org/0000-0002-0992-1899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Fu-En","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030018760","display_name":"Xiaomin Yang","orcid":"https://orcid.org/0000-0002-5593-5108"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139654144","display_name":"Nan Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139666901","display_name":"Lu Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139653079","display_name":"Min Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Min","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139671234","display_name":"Cheng-Hao Kuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuo, Cheng-Hao","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":0.8170999884605408,"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":0.8170999884605408,"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":0.04529999941587448,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.027799999341368675,"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/ground","display_name":"Ground","score":0.7731000185012817},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.7202000021934509},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4147999882698059},{"id":"https://openalex.org/keywords/single-point","display_name":"Single point","score":0.30799999833106995},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3046000003814697}],"concepts":[{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.7731000185012817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372999787330627},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.7202000021934509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49549999833106995},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C2992444157","wikidata":"https://www.wikidata.org/wiki/Q775079","display_name":"Single point","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3073999881744385},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29267","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29267","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.2606.29267","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29267","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":0.4348626732826233,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"grounding":[1,33,75,146],"aims":[2],"to":[3,73],"associate":[4],"free-form":[5],"textual":[6],"queries":[7,91],"with":[8,37,62,108],"specific":[9],"regions":[10],"in":[11,25,85],"an":[12],"image.":[13],"While":[14],"recent":[15],"Multimodal":[16],"Large":[17],"Language":[18],"Models":[19],"(MLLMs)":[20],"have":[21],"demonstrated":[22],"promising":[23],"capabilities":[24],"this":[26,50],"domain,":[27],"they":[28],"primarily":[29],"excel":[30],"at":[31],"object-level":[32],"and":[34,105,150],"often":[35],"struggle":[36],"part-level":[38,65,145],"grounding-an":[39],"essential":[40],"requirement":[41],"for":[42,121],"fine-grained":[43],"tasks":[44],"such":[45],"as":[46],"robotic":[47],"manipulation.":[48],"In":[49],"work,":[51],"we":[52,100],"introduce":[53],"a":[54,69,109,118],"general":[55],"approach":[56],"that":[57,140],"equips":[58],"any":[59,156],"open-source":[60,157],"MLLMs":[61],"accurate":[63],"2D":[64],"point":[66],"grounding,":[67],"offering":[68],"more":[70],"direct":[71],"alternative":[72],"conventional":[74],"representations.":[76],"Our":[77],"method":[78],"leverages":[79],"the":[80,96],"attention":[81,103],"mechanisms":[82],"inherently":[83],"present":[84],"MLLMs.":[86,158],"By":[87],"synthesizing":[88],"text-conditioned,":[89],"grounding-aware":[90],"within":[92],"intermediate":[93],"layers":[94],"via":[95],"proposed":[97],"Q-Synth":[98],"Module,":[99],"capture":[101],"target-relevant":[102],"patterns":[104,116],"refine":[106],"them":[107],"lightweight":[110],"Attention-to-Point":[111],"Decoder,":[112],"which":[113],"converts":[114],"these":[115],"into":[117,155],"point-centric":[119],"heatmap":[120],"final":[122],"prediction.":[123],"Notably,":[124],"all":[125],"original":[126],"MLLM":[127],"parameters":[128],"are":[129],"frozen,":[130],"ensuring":[131],"full":[132],"preservation":[133],"of":[134],"their":[135],"pre-trained":[136],"capabilities.":[137],"Experiments":[138],"show":[139],"our":[141],"design":[142],"consistently":[143],"improves":[144],"accuracy":[147],"across":[148],"datasets":[149],"can":[151],"be":[152],"seamlessly":[153],"integrated":[154]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}