{"id":"https://openalex.org/W4415163499","doi":"https://doi.org/10.1109/iccv51701.2025.00762","title":"Training-Free Generation of Temporally Consistent Rewards from VLMs","display_name":"Training-Free Generation of Temporally Consistent Rewards from VLMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415163499","doi":"https://doi.org/10.1109/iccv51701.2025.00762"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.04789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104267514","display_name":"Yinuo Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yinuo Zhao","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014607639","display_name":"Jiale Yuan","orcid":"https://orcid.org/0009-0000-3998-6768"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["KY","US"],"is_corresponding":false,"raw_author_name":"Jiale Yuan","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030569672","display_name":"Zhiyuan Xu","orcid":"https://orcid.org/0000-0002-7929-9134"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Xu","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037323143","display_name":"Xiaoshuai Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuai Hao","raw_affiliation_strings":["Beijing Academy of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381570","display_name":"Xinyi Zhang","orcid":"https://orcid.org/0009-0000-9618-5799"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Zhang","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038287652","display_name":"Kai Wu","orcid":"https://orcid.org/0000-0002-5016-0251"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wu","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079044416","display_name":"Zhengping Che","orcid":"https://orcid.org/0000-0001-6818-1125"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengping Che","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics","institution_ids":["https://openalex.org/I4210165198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102923184","display_name":"Chi Harold Liu","orcid":"https://orcid.org/0000-0002-0252-329X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Harold Liu","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101736963","display_name":"Jian Tang","orcid":"https://orcid.org/0000-0003-0332-1224"},"institutions":[{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Tang","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics","institution_ids":["https://openalex.org/I4210165198"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5104267514"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1419478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8133","last_page":"8143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.8357999920845032,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.8357999920845032,"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/T14011","display_name":"Elevator Systems and Control","score":0.8191999793052673,"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/T10205","display_name":"Advanced Fiber Optic Sensors","score":0.792900025844574,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.593500018119812},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5838000178337097},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5547000169754028},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5432999730110168},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49470001459121704},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.47510001063346863},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.43479999899864197},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3822999894618988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7185999751091003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.652999997138977},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.593500018119812},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5838000178337097},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5547000169754028},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5325999855995178},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3822999894618988},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.36090001463890076},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26899999380111694}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.00762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.04789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04789","pdf_url":"https://arxiv.org/pdf/2507.04789","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.04789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04789","pdf_url":"https://arxiv.org/pdf/2507.04789","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[{"id":"https://openalex.org/G4785052728","display_name":null,"funder_award_id":"U23A20310","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1,163],"in":[2,10,40,72,144],"vision-language":[3],"models":[4],"(VLMs)":[5],"have":[6],"significantly":[7],"improved":[8],"performance":[9,143],"embodied":[11,175],"tasks":[12],"such":[13],"as":[14],"goal":[15,107],"decomposition":[16],"and":[17,43,87,129],"visual":[18],"comprehension.":[19],"However,":[20],"providing":[21],"accurate":[22,65],"rewards":[23,66,118],"for":[24,119],"robotic":[25,38],"manipulation":[26,147],"without":[27],"fine-tuning":[28],"VLMs":[29],"remains":[30],"challenging":[31],"due":[32],"to":[33,82,104,115,170],"the":[34,69,80,106,171],"absence":[35],"of":[36,95,174],"domain-specific":[37],"knowledge":[39],"pre-trained":[41],"datasets":[42],"high":[44],"computational":[45],"costs":[46],"that":[47,63,139],"hinder":[48],"real-time":[49],"applicability.":[50],"To":[51],"address":[52],"this,":[53],"we":[54],"propose":[55],"$\\mathrm{T}^2$-VLM,":[56],"a":[57,100],"novel":[58],"training-free,":[59],"temporally":[60],"consistent":[61],"framework":[62],"generates":[64],"through":[67],"tracking":[68,102],"status":[70,109],"changes":[71],"VLM-derived":[73],"subgoals.":[74],"Specifically,":[75],"our":[76,159],"method":[77],"first":[78],"queries":[79],"VLM":[81],"establish":[83],"spatially":[84],"aware":[85],"subgoals":[86],"an":[88],"initial":[89],"completion":[90,108],"estimate":[91],"before":[92],"each":[93],"round":[94],"interaction.":[96],"We":[97,157],"then":[98],"employ":[99],"Bayesian":[101],"algorithm":[103],"update":[105],"dynamically,":[110],"using":[111],"subgoal":[112],"hidden":[113],"states":[114],"generate":[116],"structured":[117],"reinforcement":[120],"learning":[121],"(RL)":[122],"agents.":[123],"This":[124],"approach":[125,160],"enhances":[126],"long-horizon":[127],"decision-making":[128],"improves":[130],"failure":[131],"recovery":[132],"capabilities":[133],"with":[134,153],"RL.":[135],"Extensive":[136],"experiments":[137],"indicate":[138],"$\\mathrm{T}^2$-VLM":[140],"achieves":[141],"state-of-the-art":[142],"two":[145],"robot":[146],"benchmarks,":[148],"demonstrating":[149],"superior":[150],"reward":[151,164],"accuracy":[152],"reduced":[154],"computation":[155],"consumption.":[156],"believe":[158],"not":[161],"only":[162],"generation":[165],"techniques":[166],"but":[167],"also":[168],"contributes":[169],"broader":[172],"field":[173],"AI.":[176],"Project":[177],"website:":[178],"https://t2-vlm.github.io/.":[179]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-14T00:00:00"}