{"id":"https://openalex.org/W7165028228","doi":"https://doi.org/10.48550/arxiv.2606.17480","title":"GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning","display_name":"GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7165028228","doi":"https://doi.org/10.48550/arxiv.2606.17480"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.17480","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17480","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.2606.17480","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138779961","display_name":"Haoyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138796994","display_name":"Guoqing Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Guoqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138801686","display_name":"Zeyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zeyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101893660","display_name":"Yi Guo","orcid":"https://orcid.org/0009-0006-1890-6726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yandong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138823694","display_name":"Boxin Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Boxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138768652","display_name":"Hao Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, 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/T10653","display_name":"Robot Manipulation and Learning","score":0.6306999921798706,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.6306999921798706,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.10700000077486038,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.09449999779462814,"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/hallucinating","display_name":"Hallucinating","score":0.7685999870300293},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6840000152587891},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5821999907493591},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.5727999806404114},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5570999979972839},{"id":"https://openalex.org/keywords/active-vision","display_name":"Active vision","score":0.42590001225471497},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.4146000146865845},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4099000096321106},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.4075999855995178}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.7685999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7123000025749207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7035999894142151},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6840000152587891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6825000047683716},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5570999979972839},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4099000096321106},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.35899999737739563},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2849999964237213},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.17480","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17480","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.2606.17480","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17480","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":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6047168374061584}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generalist":[0],"vision-language-action":[1],"systems":[2],"need":[3],"object-centric":[4],"3D":[5,28],"evidence":[6],"and":[7,24,43,68,82,113,140,155,162,174,178,183,187,189,199,210],"reusable":[8],"manipulation":[9,47],"experience":[10],"to":[11,76],"plan":[12],"reliable":[13],"robot":[14],"trajectories.":[15],"GeneralVLA":[16],"provides":[17],"a":[18,93,129],"hierarchical":[19],"interface":[20],"for":[21],"converting":[22],"language":[23],"RGB-D":[25],"observations":[26,56],"into":[27,128],"end-effector":[29],"paths,":[30],"but":[31],"two":[32],"bottlenecks":[33],"remain.":[34],"First,":[35],"monocular":[36],"SAM3D-style":[37],"object":[38,51],"reconstruction":[39,96,151],"can":[40],"hallucinate":[41],"pose":[42],"unseen":[44],"geometry,":[45],"while":[46,117,180,205],"benefits":[48],"from":[49],"stable":[50],"shape":[52],"when":[53],"calibrated":[54],"multi-view":[55],"are":[57],"available.":[58],"Second,":[59],"the":[60,87,122,150,156,168],"original":[61],"KnowledgeBank":[62,127,190],"mainly":[63],"retrieves":[64],"semantically":[65],"similar":[66],"snippets":[67],"appends":[69],"new":[70],"knowledge,":[71],"which":[72],"makes":[73],"it":[74],"difficult":[75],"control":[77],"memory":[78,132,157],"quality,":[79,136],"conflicts,":[80],"confidence,":[81,137],"geometric":[83],"relevance.":[84],"To":[85,120],"address":[86,121],"first":[88],"challenge,":[89,124],"we":[90,125,148],"introduce":[91],"GeoFuse-MV3D,":[92],"geometry-prior-guided":[94],"MV-SAM3D":[95,169],"branch":[97,152],"that":[98],"verifies":[99],"external":[100],"geometry":[101,116],"cues":[102],"with":[103,134,144],"input-view":[104],"masks,":[105],"applies":[106],"soft":[107],"visual-hull":[108],"support,":[109],"performs":[110],"axis-wise":[111],"refinement,":[112],"fuses":[114],"only":[115],"preserving":[118],"appearance.":[119],"second":[123],"upgrade":[126],"governed":[130],"long-term":[131],"system":[133],"explicit":[135],"lifecycle,":[138],"verifier,":[139],"conflict":[141],"metadata,":[142],"together":[143],"precision-oriented":[145],"retrieval.":[146],"Finally,":[147],"evaluate":[149],"on":[153,159,196,201],"GSO-30":[154],"module":[158],"Terminal-Bench":[160,197],"2.0":[161],"SWE-Bench":[163,202],"Verified;":[164],"GeoFuse-MV3D":[165],"improves":[166,191],"over":[167,192],"baseline":[170],"by":[171,176,185,194,208],"reducing":[172,206],"CD":[173],"LPIPS":[175],"2.20%":[177],"2.02%":[179],"increasing":[181],"PSNR":[182],"SSIM":[184],"2.36%":[186],"1.03%,":[188],"ReasoningBank":[193],"4.53%":[195],"SR":[198],"3.73%":[200],"resolve":[203],"rate,":[204],"AS":[207],"4.95%":[209],"5.65%,":[211],"respectively.":[212],"Code:":[213],"https://github.com/AIGeeksGroup/GeneralVLA-2.":[214],"Website:":[215],"https://aigeeksgroup.github.io/GeneralVLA-2.":[216]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-18T00:00:00"}