{"id":"https://openalex.org/W7166854569","doi":"https://doi.org/10.18653/v1/2026.findings-acl.980","title":"GaLa: Hypergraph-Guided Visual Language Models for Procedural Planning","display_name":"GaLa: Hypergraph-Guided Visual Language Models for Procedural Planning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166854569","doi":"https://doi.org/10.18653/v1/2026.findings-acl.980"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.980","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.980","pdf_url":"https://aclanthology.org/2026.findings-acl.980.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.980.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139786644","display_name":"Kun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139727727","display_name":"Yiming Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Yiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125041211","display_name":"Mingcheng Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingcheng Qu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134135619","display_name":"Aqiang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aqiang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139716906","display_name":"Guang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guang Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139832865","display_name":"Tonghua Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tonghua Su","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87430695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19590","last_page":"19603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8075000047683716,"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":0.8075000047683716,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.02630000002682209,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.017799999564886093,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/procedural-modeling","display_name":"Procedural modeling","score":0.41690000891685486},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4050999879837036},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.375},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.30379998683929443},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2896000146865845},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2865000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.593500018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4235999882221222},{"id":"https://openalex.org/C113230428","wikidata":"https://www.wikidata.org/wiki/Q7247149","display_name":"Procedural modeling","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3684999942779541},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C124469403","wikidata":"https://www.wikidata.org/wiki/Q1813993","display_name":"Procedural knowledge","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25380000472068787},{"id":"https://openalex.org/C128644962","wikidata":"https://www.wikidata.org/wiki/Q683111","display_name":"Visual programming language","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.980","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.980","pdf_url":"https://aclanthology.org/2026.findings-acl.980.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.980","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.980","pdf_url":"https://aclanthology.org/2026.findings-acl.980.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G931605974","display_name":null,"funder_award_id":"62277011","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166854569.pdf","grobid_xml":"https://content.openalex.org/works/W7166854569.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Implicit":[0],"spatial":[1,56,64],"relations":[2,65,117],"and":[3,66,97,109,145,168,185],"deep":[4,67],"semantic":[5,39,68,116,137],"structures":[6,69],"encoded":[7],"in":[8,16,58,70,90,178],"object":[9,88],"attributes":[10,108],"are":[11,93,100],"crucial":[12],"for":[13,79],"procedural":[14,81],"planning":[15,186],"embodied":[17],"AI":[18],"systems.However,":[19],"existing":[20,176],"approaches":[21],"often":[22],"over-rely":[23],"on":[24,165],"the":[25,36,91,123,140,166],"reasoning":[26],"capabilities":[27],"of":[28,126,180],"vision":[29],"language":[30],"models":[31,50],"(VLMs)":[32],"themselves,":[33],"while":[34],"overlooking":[35],"rich":[37],"structured":[38],"information":[40],"that":[41,135,172],"can":[42],"be":[43,156],"mined":[44],"from":[45],"multimodal":[46,71,80],"inputs.As":[47],"a":[48,76,84,131],"result,":[49],"struggle":[51],"to":[52,106,155],"effectively":[53,158],"understand":[54],"functional":[55,110,127],"relationships":[57],"complex":[59],"scenes.To":[60],"fully":[61],"exploit":[62],"implicit":[63,115],"data,":[72],"we":[73,129],"propose":[74],"GaLa,":[75],"vision-language":[77],"framework":[78],"planning.GaLa":[82],"introduces":[83],"hypergraph-based":[85],"representation,":[86],"where":[87],"instances":[89],"image":[92],"modeled":[94],"as":[95,120,122],"nodes,":[96],"region-level":[98],"hyperedges":[99],"constructed":[101],"by":[102],"aggregating":[103],"objects":[104,119],"according":[105],"their":[107],"semantics.This":[111],"design":[112,130],"explicitly":[113],"captures":[114],"among":[118],"well":[121],"hierarchical":[124],"organization":[125],"regions.Furthermore,":[128],"Tri-View":[132],"HyperGraph":[133],"Encoder":[134],"enforces":[136],"consistency":[138],"across":[139],"node":[141],"view,":[142,144],"area":[143],"node-area":[146],"association":[147],"view":[148],"via":[149],"contrastive":[150],"learning,":[151],"enabling":[152],"hypergraph":[153],"semantics":[154],"more":[157],"injected":[159],"into":[160],"downstream":[161],"VLM":[162],"reasoning.Extensive":[163],"experiments":[164],"ActPlan-1K":[167],"ALFRED":[169],"benchmarks":[170],"demonstrate":[171],"GaLa":[173],"significantly":[174],"outperforms":[175],"methods":[177],"terms":[179],"execution":[181],"success":[182],"rate,":[183],"LCS,":[184],"correctness.":[187]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}