{"id":"https://openalex.org/W7161248190","doi":"https://doi.org/10.48550/arxiv.2605.14950","title":"Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model","display_name":"Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161248190","doi":"https://doi.org/10.48550/arxiv.2605.14950"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.14950","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14950","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.2605.14950","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136236284","display_name":"Tao Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136197719","display_name":"Yuxin Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Yuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003154791","display_name":"Jiting Liu","orcid":"https://orcid.org/0009-0005-4074-157X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136262705","display_name":"Nuobei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Nuobei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101823426","display_name":"Yunhe Li","orcid":"https://orcid.org/0000-0002-5656-0766"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yunhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136249456","display_name":"Yuqian Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yuqian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087953918","display_name":"Yixiang Chen","orcid":"https://orcid.org/0000-0002-3795-7530"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yinxinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136208979","display_name":"Hongyi Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Hongyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114109846","display_name":"Zewei Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Zewei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136237066","display_name":"Bing Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Bing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136233225","display_name":"Kai Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136193689","display_name":"Yiran Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Yiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136202916","display_name":"Yilei Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Yilei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036049280","display_name":"Mi Dong","orcid":"https://orcid.org/0000-0001-5373-5631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, MingKang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136213727","display_name":"Junchi Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Junchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136230745","display_name":"Gen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Gen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136212942","display_name":"Bo Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Bo","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":0.6169999837875366,"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":0.6169999837875366,"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":0.15520000457763672,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.03269999846816063,"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/software-deployment","display_name":"Software deployment","score":0.6535000205039978},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5902000069618225},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5774000287055969},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5041999816894531},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5013999938964844},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4781999886035919},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4205000102519989},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40380001068115234},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.3986999988555908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519000172615051},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6535000205039978},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5902000069618225},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5411999821662903},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5013999938964844},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4781999886035919},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4343000054359436},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C81293917","wikidata":"https://www.wikidata.org/wiki/Q4189534","display_name":"System deployment","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.14950","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14950","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.2605.14950","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14950","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"models":[1,32],"have":[2],"emerged":[3],"as":[4,29,55],"a":[5,121,143,166],"promising":[6],"paradigm":[7],"for":[8],"robotic":[9],"manipulation":[10,130],"by":[11],"unifying":[12],"perception,":[13],"language":[14],"grounding,":[15],"and":[16,43,73,79,111,228],"action":[17,193],"generation.":[18],"However,":[19],"they":[20,65],"often":[21,66,100],"struggle":[22],"in":[23,108],"scenarios":[24],"requiring":[25],"precise":[26],"spatial":[27,45,89],"understanding,":[28],"current":[30],"VLA":[31,124],"primarily":[33],"rely":[34],"on":[35,102,133],"2D":[36],"visual":[37],"representations":[38,164,190],"that":[39,126],"lack":[40],"depth":[41,56,152],"information":[42],"detailed":[44],"relationships.":[46],"While":[47],"recent":[48],"approaches":[49],"incorporate":[50],"explicit":[51],"3D":[52],"inputs":[53],"such":[54],"maps":[57],"or":[58,137],"point":[59],"clouds":[60],"to":[61,76,149,185],"address":[62,115],"this":[63],"issue,":[64],"increase":[67],"system":[68],"complexity,":[69],"require":[70],"additional":[71,134],"sensors,":[72,97],"remain":[74],"vulnerable":[75],"sensing":[77,135],"noise":[78],"reconstruction":[80],"errors.":[81],"Another":[82],"line":[83],"of":[84],"work":[85],"explores":[86],"implicit":[87],"3D-aware":[88],"modeling":[90],"directly":[91],"from":[92,154],"RGB":[93,156],"observations":[94],"without":[95,131],"extra":[96],"but":[98],"it":[99],"relies":[101],"large":[103],"geometry":[104],"foundation":[105],"models,":[106],"resulting":[107,188],"higher":[109],"training":[110],"deployment":[112,139],"costs.":[113],"To":[114],"these":[116],"challenges,":[117],"we":[118],"propose":[119],"Evo-Depth,":[120],"lightweight":[122,144],"depth-enhanced":[123,189],"framework":[125],"enhances":[127],"spatially":[128],"grounded":[129],"relying":[132],"hardware":[136],"compromising":[138],"efficiency.":[140],"Evo-Depth":[141,199,210],"employs":[142],"Implicit":[145],"Depth":[146],"Encoding":[147],"Module":[148,169],"extract":[150],"compact":[151],"features":[153,159],"multi-view":[155],"images.":[157],"These":[158],"are":[160],"incorporated":[161],"into":[162],"vision-language":[163],"through":[165],"Spatial":[167],"Enhancement":[168],"via":[170],"depth-aware":[171],"modulation,":[172],"enabling":[173],"efficient":[174],"spatial-semantic":[175],"enhancement.":[176],"A":[177],"Progressive":[178],"Alignment":[179],"Training":[180],"strategy":[181],"is":[182],"further":[183],"introduced":[184],"align":[186],"the":[187,212,220],"with":[191],"downstream":[192],"learning.":[194],"With":[195],"only":[196],"0.9B":[197],"parameters,":[198],"achieves":[200],"superior":[201],"performance":[202],"across":[203],"four":[204],"simulation":[205],"benchmarks.":[206],"In":[207],"real-world":[208],"experiments,":[209],"attains":[211],"highest":[213,229],"average":[214],"success":[215],"rate":[216],"while":[217],"also":[218],"exhibiting":[219],"smallest":[221],"model":[222],"size,":[223],"lowest":[224],"GPU":[225],"memory":[226],"usage,":[227],"inference":[230],"frequency":[231],"among":[232],"compared":[233],"methods.":[234]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-16T00:00:00"}