{"id":"https://openalex.org/W4417486099","doi":"https://doi.org/10.1109/wacv61042.2026.00408","title":"Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction","display_name":"Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417486099","doi":"https://doi.org/10.1109/wacv61042.2026.00408"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15130","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100383735","display_name":"Ce Zhang","orcid":"https://orcid.org/0000-0003-1284-7279"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ce Zhang","raw_affiliation_strings":["UNC Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I114027177","https://openalex.org/I1333535994"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100566791","display_name":"Yale Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yale Song","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074960042","display_name":"Ruta Desai","orcid":"https://orcid.org/0000-0003-4342-7699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruta Desai","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030257576","display_name":"Michael L. Iuzzolino","orcid":"https://orcid.org/0009-0006-6445-736X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Louis Iuzzolino","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002114219","display_name":"Joseph Tighe","orcid":"https://orcid.org/0000-0002-0716-8119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Tighe","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081800468","display_name":"Gedas Bertasius","orcid":"https://orcid.org/0000-0003-1800-4790"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gedas Bertasius","raw_affiliation_strings":["UNC Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNC Chapel Hill","institution_ids":["https://openalex.org/I114027177","https://openalex.org/I1333535994"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070914582","display_name":"Satwik Kottur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satwik Kottur","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03226377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4190","last_page":"4200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8944000005722046,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8944000005722046,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.020400000736117363,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.016899999231100082,"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/leverage","display_name":"Leverage (statistics)","score":0.6205000281333923},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5645999908447266},{"id":"https://openalex.org/keywords/anticipation","display_name":"Anticipation (artificial intelligence)","score":0.5414000153541565},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4771000146865845},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.3959999978542328},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38089999556541443},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.34950000047683716},{"id":"https://openalex.org/keywords/automated-planning-and-scheduling","display_name":"Automated planning and scheduling","score":0.34540000557899475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461000084877014},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6205000281333923},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5645999908447266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5548999905586243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5539000034332275},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43619999289512634},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.34950000047683716},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C84653758","wikidata":"https://www.wikidata.org/wiki/Q5575175","display_name":"Goal orientation","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26100000739097595}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv61042.2026.00408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.15130","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15130","pdf_url":"https://arxiv.org/pdf/2507.15130","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":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:2507.15130","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15130","pdf_url":"https://arxiv.org/pdf/2507.15130","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Visual":[0],"Planning":[1],"for":[2,58,91],"Assistance":[3],"(VPA)":[4],"aims":[5],"to":[6,14,71,84,96,119,126,141,157,195],"predict":[7,158],"a":[8,16,21,47],"sequence":[9],"of":[10,64,80],"user":[11],"actions":[12],"required":[13],"achieve":[15],"specified":[17],"goal":[18,124],"based":[19],"on":[20,115,171,208],"video":[22,41],"showing":[23],"the":[24,68,87,128,136,172,196,211],"user\u2019s":[25],"progress.":[26],"Although":[27],"recent":[28],"advances":[29],"in":[30,40,54],"multimodal":[31],"large":[32,56],"language":[33],"models":[34],"(MLLMs)":[35],"have":[36],"shown":[37],"promising":[38],"results":[39],"understanding,":[42],"long-horizon":[43,120],"visual":[44,92,142],"planning":[45,60,93,122,130,143],"remains":[46],"challenging":[48,197],"problem.":[49],"We":[50,109,190],"identify":[51],"two":[52],"challenges":[53],"training":[55],"MLLMs":[57],"video-based":[59,121],"tasks:":[61],"(1)":[62],"scarcity":[63],"procedural":[65,73],"annotations,":[66],"limiting":[67],"model\u2019s":[69,129],"ability":[70],"learn":[72],"task":[74],"dynamics":[75],"effectively,":[76],"and":[77,111,174,182,203],"(2)":[78],"inefficiency":[79],"next-token":[81,151],"prediction":[82,152],"objective":[83],"explicitly":[85,134],"capture":[86],"structured":[88,137],"action":[89,138],"space":[90,139],"when":[94,185],"compared":[95],"free-form,":[97],"natural":[98],"language.":[99],"To":[100,132],"tackle":[101],"data":[102],"scarcity,":[103],"we":[104,145],"introduce":[105],"Auxiliary":[106],"Task":[107],"Augmentation.":[108],"design":[110],"train":[112],"our":[113,193],"model":[114,135],"auxiliary":[116],"tasks":[117],"relevant":[118],"(e.g.,":[123],"prediction)":[125],"augment":[127],"ability.":[131],"more":[133],"unique":[140],"tasks,":[144],"leverage":[146],"Multi-token":[147],"Prediction,":[148],"extending":[149],"traditional":[150],"by":[153,180],"using":[154,216],"multiple":[155,159],"heads":[156],"future":[160,188],"tokens":[161],"during":[162],"training.":[163],"Our":[164],"approach,":[165],"VideoPlan,":[166],"achieves":[167],"state-of-the-art":[168,212],"VPA":[169],"performance":[170],"COIN":[173],"CrossTask":[175],"datasets,":[176],"surpassing":[177],"prior":[178],"methods":[179],"7.3%":[181],"3.4%,":[183],"respectively,":[184],"predicting":[186],"3":[187],"actions.":[189],"further":[191],"extend":[192],"method":[194],"Ego4D":[198],"Long-term":[199],"Action":[200],"Anticipation":[201],"task,":[202],"show":[204],"that":[205],"it":[206],"is":[207,221],"par":[209],"with":[210],"approaches":[213],"despite":[214],"not":[215],"specialized":[217],"egocentric":[218],"features.":[219],"Code":[220],"available":[222],"at":[223],"https://github.com/CeeZh/VideoPlan.":[224]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}