{"id":"https://openalex.org/W4416749539","doi":"https://doi.org/10.1109/iros60139.2025.11245824","title":"ToSA: Token Merging with Spatial Awareness","display_name":"ToSA: Token Merging with Spatial Awareness","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749539","doi":"https://doi.org/10.1109/iros60139.2025.11245824"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5101699930","display_name":"Hsiang-Wei Huang","orcid":"https://orcid.org/0000-0003-0373-9487"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210138199","display_name":"University of Washington Applied Physics Laboratory","ror":"https://ror.org/03d17d270","country_code":"US","type":"facility","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hsiang-Wei Huang","raw_affiliation_strings":["University of Washington,Electrical and Computer Engineering Department"],"affiliations":[{"raw_affiliation_string":"University of Washington,Electrical and Computer Engineering Department","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103021774","display_name":"Wenhao Chai","orcid":"https://orcid.org/0000-0003-2611-0008"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210138199","display_name":"University of Washington Applied Physics Laboratory","ror":"https://ror.org/03d17d270","country_code":"US","type":"facility","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenhao Chai","raw_affiliation_strings":["University of Washington,Electrical and Computer Engineering Department"],"affiliations":[{"raw_affiliation_string":"University of Washington,Electrical and Computer Engineering Department","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072487344","display_name":"Kuang-Ming Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138199","display_name":"University of Washington Applied Physics Laboratory","ror":"https://ror.org/03d17d270","country_code":"US","type":"facility","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuang-Ming Chen","raw_affiliation_strings":["University of Washington,Electrical and Computer Engineering Department"],"affiliations":[{"raw_affiliation_string":"University of Washington,Electrical and Computer Engineering Department","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047672937","display_name":"Cheng-Yen Yang","orcid":"https://orcid.org/0009-0004-2631-6756"},"institutions":[{"id":"https://openalex.org/I4210138199","display_name":"University of Washington Applied Physics Laboratory","ror":"https://ror.org/03d17d270","country_code":"US","type":"facility","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng-Yen Yang","raw_affiliation_strings":["University of Washington,Electrical and Computer Engineering Department"],"affiliations":[{"raw_affiliation_string":"University of Washington,Electrical and Computer Engineering Department","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101702810","display_name":"Jenq\u2013Neng Hwang","orcid":"https://orcid.org/0000-0002-8877-2421"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210138199","display_name":"University of Washington Applied Physics Laboratory","ror":"https://ror.org/03d17d270","country_code":"US","type":"facility","lineage":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jenq-Neng Hwang","raw_affiliation_strings":["University of Washington,Electrical and Computer Engineering Department"],"affiliations":[{"raw_affiliation_string":"University of Washington,Electrical and Computer Engineering Department","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I4210138199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101699930"],"corresponding_institution_ids":["https://openalex.org/I201448701","https://openalex.org/I4210138199"],"apc_list":null,"apc_paid":null,"fwci":1.428,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87492625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9654","last_page":"9660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4571000039577484,"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":0.4571000039577484,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.14350000023841858,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.10700000077486038,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.9085999727249146},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.43380001187324524},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4049000144004822},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3783000111579895},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.37700000405311584},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.9085999727249146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839000225067139},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C115067241","wikidata":"https://www.wikidata.org/wiki/Q1639854","display_name":"Token passing","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2963518342","https://openalex.org/W3188427387","https://openalex.org/W4312849330","https://openalex.org/W4319300012","https://openalex.org/W4386076539","https://openalex.org/W4389519587","https://openalex.org/W4390873312","https://openalex.org/W4402671548","https://openalex.org/W4402716288","https://openalex.org/W4402727764","https://openalex.org/W4402727885","https://openalex.org/W4402754220","https://openalex.org/W4402776116","https://openalex.org/W4403002096","https://openalex.org/W4403725941","https://openalex.org/W4403939369","https://openalex.org/W4413145638","https://openalex.org/W4413926275","https://openalex.org/W4415798746","https://openalex.org/W4415800665"],"related_works":[],"abstract_inverted_index":{"Token":[0],"merging":[1,47,72,85,109,121,137],"has":[2],"emerged":[3],"as":[4,41,92,101],"an":[5,158],"effective":[6],"strategy":[7,122],"to":[8,81,94],"accelerate":[9],"Vision":[10],"Transformers":[11],"(ViT)":[12],"by":[13],"reducing":[14,150],"computational":[15],"costs.":[16],"However,":[17],"existing":[18],"methods":[19,138],"primarily":[20],"rely":[21],"on":[22,142],"the":[23,32,49,55,83,89,106,112,151,154],"visual":[24,56,61,107,143],"token\u2019s":[25],"feature":[26],"similarity":[27],"for":[28,45,105,161],"token":[29,46,71,84,108,136],"merging,":[30],"overlooking":[31],"potential":[33],"of":[34,52,153],"integrating":[35],"spatial":[36,79,97,103,114],"information,":[37],"which":[38,99],"can":[39],"serve":[40,100],"a":[42,69,118],"reliable":[43],"criterion":[44],"in":[48],"early":[50],"layers":[51],"ViT,":[53,155],"where":[54],"tokens":[57],"only":[58],"possess":[59],"weak":[60],"information.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"propose":[67],"ToSA,":[68],"novel":[70],"method":[73],"that":[74,123,132],"combines":[75],"both":[76],"semantic":[77],"and":[78,144],"awareness":[80],"guide":[82],"process.":[86,110],"ToSA":[87,116,133],"leverages":[88],"depth":[90],"image":[91],"input":[93],"generate":[95],"pseudo":[96],"tokens,":[98],"auxiliary":[102],"information":[104],"With":[111],"introduced":[113],"awareness,":[115],"achieves":[117],"more":[119],"informed":[120],"better":[124],"preserves":[125],"critical":[126],"scene":[127],"structure.":[128],"Experimental":[129],"results":[130],"demonstrate":[131],"outperforms":[134],"previous":[135],"across":[139],"multiple":[140],"benchmarks":[141],"embodied":[145],"question":[146],"answering":[147],"while":[148],"largely":[149],"runtime":[152],"making":[156],"it":[157],"efficient":[159],"solution":[160],"ViT":[162],"acceleration.":[163],"The":[164],"code":[165],"will":[166],"be":[167],"available":[168],"at:":[169],"https://github.com/hsiangwei0903/ToSA.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}