{"id":"https://openalex.org/W7164925006","doi":"https://doi.org/10.48550/arxiv.2606.14981","title":"Inference-time Policy Steering via Vision and Touch","display_name":"Inference-time Policy Steering via Vision and Touch","publication_year":2026,"publication_date":"2026-06-12","ids":{"openalex":"https://openalex.org/W7164925006","doi":"https://doi.org/10.48550/arxiv.2606.14981"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.14981","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14981","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,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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.2606.14981","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138697559","display_name":"Yilin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025075748","display_name":"Zilin Si","orcid":"https://orcid.org/0000-0002-1111-4279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Si, Zilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138749116","display_name":"Zeynep Temel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Temel, Zeynep","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033201561","display_name":"O. Kroemer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kroemer, Oliver","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136058920","display_name":"Andrea Bajcsy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bajcsy, Andrea","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":0.7962999939918518,"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":0.7962999939918518,"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/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.034299999475479126,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10709","display_name":"Social Robot Interaction and HRI","score":0.027799999341368675,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.616599977016449},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5730000138282776},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.48179998993873596},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4050999879837036},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.35530000925064087},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.35089999437332153},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33340001106262207},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3271999955177307},{"id":"https://openalex.org/keywords/visual-servoing","display_name":"Visual servoing","score":0.3052000105381012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6697999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6399999856948853},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.616599977016449},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5730000138282776},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4643000066280365},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41690000891685486},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.35089999437332153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C17511633","wikidata":"https://www.wikidata.org/wiki/Q830694","display_name":"SMT placement equipment","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.26330000162124634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.14981","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14981","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,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.14981","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.14981","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,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":{"Inference-time":[0],"steering":[1,56,157],"adapts":[2],"pre-trained":[3],"generative":[4],"robot":[5,81],"policies":[6],"during":[7],"deployment":[8],"by":[9,149,158,167],"verifying":[10],"candidate":[11],"actions":[12],"before":[13],"execution.":[14],"While":[15],"prior":[16],"methods":[17],"typically":[18],"perform":[19],"this":[20],"verification":[21],"only":[22],"with":[23],"visual":[24,71,120],"observations,":[25],"vision":[26],"alone":[27],"is":[28],"often":[29],"insufficient":[30],"for":[31],"contact-rich":[32,142],"manipulation,":[33],"where":[34],"success":[35,148],"depends":[36],"on":[37],"both":[38],"global":[39],"task":[40],"progress":[41],"and":[42,116,121,162],"subtle":[43],"local":[44,102],"interactions":[45],"such":[46],"as":[47,62],"contact":[48,103],"force.":[49],"We":[50],"introduce":[51],"ViTaL,":[52],"a":[53,63,97,111,125],"visuo-tactile":[54,112],"inference-time":[55],"framework":[57],"that":[58,130],"formulates":[59],"multimodal":[60,165],"guidance":[61],"bi-level":[64],"optimization":[65],"problem.":[66],"At":[67,84],"the":[68,80,85,92,152],"high":[69],"level,":[70,87],"sampling-and-verification":[72],"performs":[73],"long-horizon":[74],"mode":[75],"selection,":[76],"deciding":[77],"what":[78],"behavior":[79],"should":[82],"execute.":[83],"low":[86],"tactile-guided":[88],"diffusion":[89],"editing":[90],"refines":[91],"selected":[93],"action":[94],"sequence":[95],"over":[96,151],"shorter":[98],"horizon":[99],"to":[100],"satisfy":[101],"requirements.":[104],"To":[105],"support":[106],"outcome-based":[107],"steering,":[108],"ViTaL":[109,145],"learns":[110],"latent":[113,137],"world":[114],"model":[115],"employs":[117],"semantically":[118],"aligned":[119],"tactile":[122,128,133],"verifiers,":[123],"including":[124],"novel":[126],"text-conditioned":[127],"reward":[129],"scores":[131],"predicted":[132],"futures":[134],"directly":[135],"in":[136],"space.":[138],"Across":[139],"three":[140],"real-world":[141],"manipulation":[143],"tasks,":[144],"improves":[146],"overall":[147],"51%":[150],"base":[153],"policy,":[154],"outperforms":[155],"unimodal":[156],"at":[159,168],"least":[160,169],"33%,":[161],"exceeds":[163],"naive":[164],"fusion":[166],"20%.":[170],"Website:":[171],"https://yilin-wu98.github.io/vital_website.":[172]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-17T00:00:00"}
