{"id":"https://openalex.org/W7163445706","doi":"https://doi.org/10.48550/arxiv.2606.03954","title":"VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring","display_name":"VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163445706","doi":"https://doi.org/10.48550/arxiv.2606.03954"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.03954","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03954","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.2606.03954","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039258932","display_name":"Hanjiang Hu","orcid":"https://orcid.org/0000-0002-5698-5887"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Hanjiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137773331","display_name":"Yiyuan Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Yiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137758785","display_name":"Jiaxing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiaxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009405571","display_name":"Xusheng Luo","orcid":"https://orcid.org/0000-0003-4342-7234"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Xusheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137728351","display_name":"Alexander Robey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robey, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137728978","display_name":"Na Li (6550)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Na","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044079782","display_name":"Yebin Wang","orcid":"https://orcid.org/0000-0001-7209-7866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yebin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137738025","display_name":"Changliu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Changliu","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/T10812","display_name":"Human Pose and Action Recognition","score":0.5458999872207642,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.5458999872207642,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.16339999437332153,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.039400000125169754,"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/embodied-cognition","display_name":"Embodied cognition","score":0.694100022315979},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6360999941825867},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.592199981212616},{"id":"https://openalex.org/keywords/intervention","display_name":"Intervention (counseling)","score":0.4212999939918518},{"id":"https://openalex.org/keywords/psychological-intervention","display_name":"Psychological intervention","score":0.41909998655319214},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41690000891685486},{"id":"https://openalex.org/keywords/system-safety","display_name":"System safety","score":0.3788999915122986}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.694100022315979},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5939000248908997},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.592199981212616},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44190001487731934},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41690000891685486},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4131999909877777},{"id":"https://openalex.org/C132835097","wikidata":"https://www.wikidata.org/wiki/Q7663745","display_name":"System safety","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C2777488183","wikidata":"https://www.wikidata.org/wiki/Q6900510","display_name":"Safety monitoring","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C169806903","wikidata":"https://www.wikidata.org/wiki/Q5937752","display_name":"Human error","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.03954","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03954","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.2606.03954","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03954","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":[{"score":0.6073358058929443,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"AI":[1],"systems":[2],"increasingly":[3],"assist":[4],"humans":[5],"in":[6],"physical":[7,14],"tasks,":[8],"ensuring":[9],"safety":[10,46,56,75,82,140],"becomes":[11],"paramount":[12],"--":[13],"actions":[15,50,59,89,114],"carry":[16],"immediate":[17],"and":[18,43,111],"irreversible":[19],"consequences":[20],"that":[21,36,87],"digital":[22],"errors":[23],"do":[24],"not.":[25],"We":[26],"introduce":[27],"the":[28,118,127,135],"Vision-Language":[29],"Embodied":[30],"Safety":[31],"Agent":[32],"(VLESA),":[33],"a":[34,80],"framework":[35],"monitors":[37],"human":[38],"activities":[39],"from":[40,115],"egocentric":[41,71],"video":[42],"triggers":[44],"real-time":[45],"interventions":[47],"when":[48],"dangerous":[49,64],"are":[51],"predicted.":[52],"VLESA":[53,121],"addresses":[54],"intent-dependent":[55],"where":[57],"identical":[58],"can":[60],"be":[61],"safe":[62],"or":[63],"depending":[65],"on":[66],"context.":[67],"A":[68],"dataset":[69],"pairing":[70],"frames":[72],"with":[73,90],"goal-conditioned":[74,81,147],"annotations":[76],"is":[77,105,151],"introduced,":[78],"enabling":[79],"Q-filter":[83,137],"trained":[84],"via":[85],"GRPO":[86],"evaluates":[88],"respect":[91],"to":[92,107,132],"inferred":[93],"intent":[94],"without":[95],"retraining.":[96],"On":[97,117],"top":[98],"of":[99],"that,":[100],"an":[101],"intent-action":[102],"prediction":[103],"agent":[104],"proposed":[106],"jointly":[108],"infer":[109],"goals":[110],"predict":[112],"future":[113],"video.":[116],"ASIMOV-2.0":[119],"benchmark,":[120],"achieves":[122],"higher":[123],"intervention":[124],"accuracy":[125],"at":[126,153],"exact":[128],"ground-truth":[129],"frame":[130],"compared":[131],"baselines,":[133],"while":[134],"GRPO-trained":[136],"improves":[138],"action":[139],"by":[141],"over":[142],"41":[143],"percentage":[144],"points":[145],"through":[146],"constrained":[148],"decoding.":[149],"Code":[150],"available":[152],"https://github.com/HanjiangHu/VLESA.":[154]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-04T00:00:00"}