{"id":"https://openalex.org/W7137929582","doi":"https://doi.org/10.48550/arxiv.2603.13788","title":"ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation","display_name":"ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137929582","doi":"https://doi.org/10.48550/arxiv.2603.13788"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.13788","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13788","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2603.13788","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129706710","display_name":"You Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, You","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129649838","display_name":"Zixuan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129714358","display_name":"Cunxu Ou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ou, Cunxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129671106","display_name":"Wenxuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129707173","display_name":"Wenbo Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Wenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103020772","display_name":"Lin Cao","orcid":"https://orcid.org/0000-0003-1032-065X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129688754","display_name":"Yangtao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yangtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129724070","display_name":"Weichao Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Weichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129649178","display_name":"Xingyue Quan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan, Xingyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129641964","display_name":"Jieqi Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Jieqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129670745","display_name":"Jing Huo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huo, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129645635","display_name":"Yang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yang","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":0.5637000203132629,"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":0.5637000203132629,"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":0.3271999955177307,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.01979999989271164,"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/robustness","display_name":"Robustness (evolution)","score":0.6729000210762024},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5356000065803528},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.516700029373169},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4659000039100647},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46050000190734863},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4431000053882599},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.43970000743865967},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.38830000162124634}],"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/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6729000210762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237000226974487},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5356000065803528},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46050000190734863},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44699999690055847},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4431000053882599},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.13788","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13788","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.13788","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13788","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Robotic":[0],"manipulation":[1,100,164],"in":[2,39],"open-world":[3,200],"environments":[4],"requires":[5],"reasoning":[6,26,83,187],"across":[7],"semantics,":[8],"geometry,":[9],"and":[10,34,58,67,84,105,112,132,149,156,162,179,197],"long-horizon":[11,157],"action":[12],"dynamics.":[13],"Existing":[14],"hierarchical":[15,47],"Vision-Language-Action":[16],"(VLA)":[17],"frameworks":[18],"typically":[19],"use":[20],"2D":[21,62],"representations":[22,136,193],"to":[23,55,137,188],"connect":[24],"high-level":[25],"with":[27,102,109,190],"low-level":[28],"control,":[29],"but":[30],"lack":[31],"depth":[32],"awareness":[33],"temporal":[35],"consistency,":[36],"limiting":[37],"robustness":[38,196],"complex":[40],"3D":[41,65,135],"scenes.":[42],"We":[43],"propose":[44],"ST-VLA,":[45],"a":[46,51,78,97,116,124],"VLA":[48],"framework":[49],"using":[50],"unified":[52,191],"3D-4D":[53,192],"representation":[54],"bridge":[56],"perception":[57],"action.":[59],"ST-VLA":[60],"converts":[61],"guidance":[63],"into":[64],"trajectories":[66],"generates":[68,129],"smooth":[69,142],"spatial":[70,143],"masks":[71,144],"that":[72,128,167,184],"capture":[73],"4D":[74,113],"spatio-temporal":[75,125,186],"context,":[76],"providing":[77],"stable":[79],"interface":[80],"between":[81],"semantic":[82],"continuous":[85],"control.":[86],"To":[87],"enable":[88],"effective":[89],"learning":[90],"of":[91],"such":[92],"representations,":[93,152],"we":[94,121],"introduce":[95],"ST-Human,":[96,120],"large-scale":[98],"human":[99],"dataset":[101],"14":[103],"tasks":[104,165],"300k":[106],"episodes,":[107],"annotated":[108],"2D,":[110],"3D,":[111],"supervision":[114],"via":[115],"semi-automated":[117],"pipeline.":[118],"Using":[119],"train":[122],"ST-VLM,":[123],"vision-language":[126],"model":[127],"spatially":[130],"grounded":[131],"temporally":[133],"coherent":[134],"guide":[138],"policy":[139],"execution.":[140],"The":[141],"focus":[145],"on":[146,160],"task-relevant":[147],"geometry":[148],"stabilize":[150],"latent":[151],"enabling":[153],"online":[154],"replanning":[155],"reasoning.":[158],"Experiments":[159],"RLBench":[161],"real-world":[163],"show":[166],"\\method":[168],"significantly":[169],"outperforms":[170],"state-of-the-art":[171],"baselines,":[172],"improving":[173],"zero-shot":[174],"success":[175],"rates":[176],"by":[177],"44.6%":[178],"30.3%.":[180],"These":[181],"results":[182],"demonstrate":[183],"offloading":[185],"VLMs":[189],"substantially":[194],"improves":[195],"generalization":[198],"for":[199],"robotic":[201],"manipulation.":[202],"Project":[203],"website:":[204],"https://oucx117.github.io/ST-VLA/.":[205]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-18T00:00:00"}