{"id":"https://openalex.org/W7214920191","doi":"https://doi.org/10.48550/arxiv.2609.37519","title":"Video2STL: Grounding VLM-Generated Temporal Specifications for Robot Learning","display_name":"Video2STL: Grounding VLM-Generated Temporal Specifications for Robot Learning","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214920191","doi":"https://doi.org/10.48550/arxiv.2609.37519"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37519","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37519","pdf_url":"https://arxiv.org/pdf/2609.37519","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37519","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114336086","display_name":"Merve Atasever","orcid":"https://orcid.org/0000-0001-8400-5412","observed_orcids":["https://orcid.org/0000-0001-8400-5412","https://orcid.org/0000-0001-9743-1488"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atasever, Merve","raw_affiliation_strings":["Department of Computer Science , University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140009476","display_name":"Keyan Azbijari","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Azbijari, Keyan","raw_affiliation_strings":["Department of Computer Science , University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139985724","display_name":"Cagan Bakirci","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bakirci, Cagan","raw_affiliation_strings":["Department of Computer Science , University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081382003","display_name":"Bo-Ruei Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Bo-Ruei","raw_affiliation_strings":["Department of Computer Science , University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117632835","display_name":"Tolga \u0130zda\u015f","orcid":"https://orcid.org/0009-0007-3643-3990","observed_orcids":["https://orcid.org/0009-0007-3643-3990"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Izdas, Tolga","raw_affiliation_strings":["Department of Computer Science , University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016214463","display_name":"Zahra Shahrooei","orcid":"https://orcid.org/0009-0008-7899-0514","observed_orcids":["https://orcid.org/0009-0008-7899-0514"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shahrooei, Zahra","raw_affiliation_strings":["Department of Computer Science , University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150905080","display_name":"Richard Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Richard","raw_affiliation_strings":["University of Florida Gainesville , FL , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida Gainesville , FL , USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031426401","display_name":"Erdem B\u0131y\u0131k","orcid":"https://orcid.org/0000-0002-9516-3130","observed_orcids":["https://orcid.org/0000-0002-9516-3130"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biyik, Erdem","raw_affiliation_strings":["Department of Computer Science , University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057473400","display_name":"Jyotirmoy V. Deshmukh","orcid":"https://orcid.org/0000-0003-4683-5540","observed_orcids":["https://orcid.org/0000-0003-4683-5540","https://orcid.org/0000-0002-8815-464X"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deshmukh, Jyotirmoy V.","raw_affiliation_strings":["Department of Computer Science , University of Southern California Los Angeles , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Southern California Los Angeles , CA , USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7465999722480774,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7465999722480774,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.2280000001192093,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.004800000227987766,"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/signal-temporal-logic","display_name":"signal temporal logic","score":0.8019999861717224},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9700000286102295},{"id":"https://openalex.org/keywords/robot-policy-learning","display_name":"robot policy learning","score":0.4959999918937683},{"id":"https://openalex.org/keywords/cross-embodiment-transfer","display_name":"cross-embodiment transfer","score":0.824999988079071},{"id":"https://openalex.org/keywords/manipulation-tasks","display_name":"manipulation tasks","score":0.5580000281333923},{"id":"https://openalex.org/keywords/quadrupedal-locomotion","display_name":"quadrupedal locomotion","score":0.9940000176429749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.675599992275238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6115000247955322},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41260001063346863},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3917999863624573},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3052999973297119},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2621000111103058},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C18460168","wikidata":"https://www.wikidata.org/wiki/Q5416707","display_name":"Event calculus","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37519","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37519","pdf_url":"https://arxiv.org/pdf/2609.37519","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2609.37519","doi":"https://doi.org/10.48550/arxiv.2609.37519","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37519","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37519","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37519","pdf_url":"https://arxiv.org/pdf/2609.37519","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214920191.pdf","grobid_xml":"https://content.openalex.org/works/W7214920191.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387636048","https://openalex.org/W4417086207","https://openalex.org/W4416552080","https://openalex.org/W7170120414","https://openalex.org/W4416189451","https://openalex.org/W4402354080","https://openalex.org/W7125496427","https://openalex.org/W4402354026","https://openalex.org/W7162685497","https://openalex.org/W7133231380"],"abstract_inverted_index":{"Video-based":[0],"policy":[1,133],"learning":[2],"is":[3,21],"particularly":[4],"promising,":[5],"as":[6],"it":[7],"illustrates":[8],"target":[9],"behaviors":[10],"without":[11],"requiring":[12],"action":[13],"annotations":[14],"or":[15,43,46,176],"embodiment-matched":[16],"demonstrations.":[17],"A":[18,96],"central":[19],"challenge":[20],"deciding":[22],"what":[23],"information":[24],"should":[25],"be":[26],"transferred":[27],"from":[28,128,174,218],"the":[29,32,59,89,116],"video":[30],"to":[31,50,66,179,220],"robot.":[33],"Existing":[34],"approaches":[35,56],"commonly":[36],"convert":[37],"visual":[38],"observations":[39],"into":[40,80],"scalar":[41],"similarity":[42],"value":[44],"signals,":[45],"ask":[47],"foundation":[48],"models":[49],"directly":[51],"generate":[52],"reward":[53],"code.":[54],"These":[55],"can":[57],"make":[58],"temporal":[60,111,124,140,166],"structure":[61],"of":[62,109],"a":[63,74,107,152,156],"task":[64,117],"difficult":[65],"inspect,":[67],"ground,":[68],"and":[69,87,105,123,138,191,201,209],"reuse.":[70],"We":[71],"present":[72],"Video2STL,":[73],"framework":[75],"that":[76],"converts":[77],"observation-only":[78],"videos":[79,178],"parametric":[81],"Signal":[82],"Temporal":[83],"Logic":[84],"(STL)":[85],"specifications":[86,143],"uses":[88],"resulting":[90],"formal":[91],"representation":[92,170],"for":[93,164,197,203],"robot":[94,130,180],"learning.":[95],"vision-language":[97],"model":[98,114],"extracts":[99],"an":[100],"embodiment-independent":[101],"semantic":[102],"event":[103],"trace":[104],"constructs":[106],"bank":[108],"symbolic":[110],"specifications.":[112],"The":[113,168],"determines":[115],"structure,":[118],"while":[119,151,222],"numerical":[120],"predicate":[121],"thresholds":[122],"bounds":[125],"are":[126],"grounded":[127],"successful":[129],"trajectories.":[131],"For":[132],"learning,":[134],"we":[135],"separate":[136],"short-":[137],"long-timescale":[139],"information:":[141],"short-horizon":[142],"provide":[144],"dense":[145,199],"rewards":[146,163],"through":[147],"rolling-window":[148],"quantitative":[149],"robustness,":[150],"causal":[153],"monitor":[154],"over":[155],"retained":[157],"long-horizon":[158],"specification":[159],"provides":[160],"one-time":[161],"progress":[162],"valid":[165],"prefixes.":[167],"same":[169],"supports":[171],"cross-embodiment":[172],"transfer":[173],"human":[175],"animal":[177],"control.":[181],"Across":[182],"four":[183],"manipulation":[184],"tasks,":[185],"Video2STL":[186,211],"achieves":[187],"$85.8\\%$":[188],"average":[189],"success-once":[190],"$67.0\\%$":[192],"success-at-end,":[193],"compared":[194],"with":[195],"$81.5\\%/59.5\\%$":[196],"native":[198],"PPO":[200],"$65.0\\%/42.3\\%$":[202],"Text2Reward;":[204],"in":[205,225],"quadruped":[206],"locomotion,":[207],"Qwen-3.8":[208],"GPT-5.6-based":[210],"policies":[212],"achieve":[213],"$100\\%$":[214],"success":[215],"across":[216],"velocities":[217],"$0.3$":[219],"$2.1\\,\\mathrm{m/s}$":[221],"remaining":[223],"competitive":[224],"high-speed":[226],"energy":[227],"efficiency.":[228],"Project":[229],"webpage:":[230],"\\href{https://video2stl.github.io/}{video2stl}.":[231]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-01T00:00:00"}