{"id":"https://openalex.org/W7123792645","doi":"https://doi.org/10.1109/tpami.2026.3653482","title":"Goal-Guided Prompting With Adaptive Modality Selection for Efficient Assembly Activity Anticipation in Egocentric Videos","display_name":"Goal-Guided Prompting With Adaptive Modality Selection for Efficient Assembly Activity Anticipation in Egocentric Videos","publication_year":2026,"publication_date":"2026-01-13","ids":{"openalex":"https://openalex.org/W7123792645","doi":"https://doi.org/10.1109/tpami.2026.3653482","pmid":"https://pubmed.ncbi.nlm.nih.gov/41528910"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3653482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3653482","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122972753","display_name":"Tianshan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshan Liu","raw_affiliation_strings":["School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122981270","display_name":"Bing-Kun Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5956-831X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05680123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"5","first_page":"5945","last_page":"5962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10888","display_name":"Augmented Reality Applications","score":0.717199981212616,"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/T10888","display_name":"Augmented Reality Applications","score":0.717199981212616,"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":0.04270000010728836,"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/T10648","display_name":"Virtual Reality Applications and Impacts","score":0.040800001472234726,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/modalities","display_name":"Modalities","score":0.6807000041007996},{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.6791999936103821},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6193000078201294},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4948999881744385},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.48399999737739563},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.46540001034736633},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.4390000104904175},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4325000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612000107765198},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6807000041007996},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.6791999936103821},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6193000078201294},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5347999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5342000126838684},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.48399999737739563},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.4390000104904175},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4092999994754791},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C26486553","wikidata":"https://www.wikidata.org/wiki/Q371870","display_name":"Stimulus modality","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.26100000739097595}],"mesh":[{"descriptor_ui":"D000081411","descriptor_name":"Augmented Reality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081411","descriptor_name":"Augmented Reality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081411","descriptor_name":"Augmented Reality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081411","descriptor_name":"Augmented Reality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081411","descriptor_name":"Augmented Reality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081411","descriptor_name":"Augmented Reality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081411","descriptor_name":"Augmented Reality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081411","descriptor_name":"Augmented Reality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000081411","descriptor_name":"Augmented Reality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098403","descriptor_name":"Intelligent Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098403","descriptor_name":"Intelligent Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098403","descriptor_name":"Intelligent Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098403","descriptor_name":"Intelligent Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098403","descriptor_name":"Intelligent Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098426","descriptor_name":"Adaptive Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098426","descriptor_name":"Adaptive Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098426","descriptor_name":"Adaptive Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098426","descriptor_name":"Adaptive Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098426","descriptor_name":"Adaptive Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006040","descriptor_name":"Goals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006040","descriptor_name":"Goals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006040","descriptor_name":"Goals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006040","descriptor_name":"Goals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3653482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3653482","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41528910","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41528910","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.7572968006134033,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G1362912382","display_name":null,"funder_award_id":"62532003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2059522383","display_name":null,"funder_award_id":"BK20240646","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G264948653","display_name":null,"funder_award_id":"62402243","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3087610523","display_name":null,"funder_award_id":"U23A20387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5851403343","display_name":null,"funder_award_id":"62325206","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"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","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":{"With":[0],"the":[1,15,22,42,64,67,120,124,133,139,178,182,191,201,229,243,248,251,259,276],"functions":[2],"of":[3,18,157,193,250],"egocentric":[4,69,116],"observation":[5,235],"and":[6,28,59,82,127,173],"multimodal":[7,195],"perception":[8],"equipped":[9],"in":[10,32,61,90,97,115,284,291],"augmented":[11],"reality":[12],"(AR)":[13],"devices,":[14],"next":[16],"generation":[17],"smart":[19],"assistants":[20],"has":[21],"potential":[23],"to":[24,56,75,87,146,153,176,211,218,242],"reduce":[25],"human":[26],"labor":[27],"enhance":[29],"execution":[30],"efficiency":[31,249],"assembly":[33,37,112,183],"tasks.":[34],"Among":[35],"diverse":[36],"activity":[38,70,113],"understanding":[39],"tasks,":[40],"anticipating":[41],"near":[43],"future":[44,129],"activities":[45,184],"is":[46,164,209],"crucial":[47],"yet":[48],"challenging,":[49],"which":[50,142,216,221],"can":[51,254],"assist":[52],"humans":[53],"or":[54],"agents":[55],"actively":[57],"plan":[58],"engage":[60],"interactions":[62],"with":[63,106,166],"environment.":[65],"However,":[66],"existing":[68],"anticipation":[71,114,230,285],"methods":[72],"still":[73],"struggle":[74],"achieve":[76],"a":[77,102,148,161,186,213,233],"decent":[78],"trade-off":[79],"between":[80,123,181],"accuracy":[81],"computational":[83,202],"efficiency,":[84],"hindering":[85],"them":[86],"be":[88,224,255],"deployed":[89],"practical":[91],"applications.":[92],"To":[93],"address":[94],"this":[95,98],"dilemma,":[96],"paper,":[99],"we":[100,131],"propose":[101],"goal-guided":[103],"prompting":[104],"framework":[105],"adaptive":[107,205],"modality":[108,206],"selection":[109,207],"(GP-AMS),":[110],"for":[111,226,261],"videos.":[117],"For":[118,189],"bridging":[119],"semantic":[121],"gap":[122],"historical":[125],"observations":[126],"unobserved":[128],"activities,":[130],"inject":[132],"inferred":[134],"high-level":[135],"goal":[136],"clues":[137],"into":[138],"constructed":[140],"prompts,":[141],"are":[143],"further":[144],"utilized":[145],"guide":[147],"pre-trained":[149],"vision-language":[150],"(V-L)":[151],"model":[152,231,253],"compensate":[154],"relevant":[155],"semantics":[156],"unseen":[158],"future.":[159],"Moreover,":[160],"mask-and-predict":[162],"strategy":[163,208],"adopted":[165],"two":[167,270],"imposed":[168],"constraints,":[169],"i.e.,":[170],"casual":[171],"masking":[172],"probabilistic":[174],"token-dropping,":[175],"mine":[177],"intrinsic":[179],"associations":[180],"within":[185],"specific":[187],"procedure.":[188],"maintaining":[190],"benefits":[192],"exploiting":[194],"information":[196],"while":[197],"avoiding":[198],"extensively":[199],"increasing":[200],"burdens,":[203],"an":[204],"designed":[210],"train":[212],"policy":[214],"network,":[215],"learns":[217],"dynamically":[219],"decide":[220],"modalities":[222,246],"should":[223],"sampled":[225],"processing":[227],"by":[228],"on":[232,263,269],"per":[234],"time-step":[236],"basis.":[237],"By":[238],"allocating":[239],"major":[240],"computation":[241,292],"selected":[244],"indicative":[245],"on-the-fly,":[247],"overall":[252],"improved,":[256],"thus":[257],"paving":[258],"way":[260],"feasibility":[262],"real-world":[264],"devices.":[265],"Extensive":[266],"experimental":[267],"results":[268],"public":[271],"data":[272],"sets":[273],"validate":[274],"that":[275],"proposed":[277],"method":[278],"yields":[279],"not":[280],"only":[281],"consistent":[282],"improvements":[283],"accuracy,":[286],"but":[287],"also":[288],"significant":[289],"savings":[290],"budgets.":[293]},"counts_by_year":[],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2026-01-14T00:00:00"}