{"id":"https://openalex.org/W7138097411","doi":"https://doi.org/10.1609/aaai.v40i22.38904","title":"SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation","display_name":"SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138097411","doi":"https://doi.org/10.1609/aaai.v40i22.38904"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38904","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38904","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i22.38904","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129694510","display_name":"Wei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103115471","display_name":"Renshan Zhang","orcid":"https://orcid.org/0000-0003-1833-9996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renshan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129643381","display_name":"Rui Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Shao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017105526","display_name":"Zhijian Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhijian Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129703962","display_name":"Kaiwen Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiwen Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129699623","display_name":"Zhuotao Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuotao Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129684253","display_name":"Liqiang Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":0.35897436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18397","last_page":"18405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3237999975681305,"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":0.3237999975681305,"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":0.2547000050544739,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11270000040531158,"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/semantics","display_name":"Semantics (computer science)","score":0.5716000199317932},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5547999739646912},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.511900007724762},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5008999705314636},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.492900013923645},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4909000098705292},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43549999594688416},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.42089998722076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398999929428101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6182000041007996},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5716000199317932},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5547999739646912},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4909000098705292},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.42089998722076416},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3312999904155731},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27309998869895935},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2696000039577484}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38904","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38904","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i22.38904","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38904","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2],"have":[3],"advanced":[4],"in":[5,85,96,168,181],"robotic":[6],"manipulation,":[7],"yet":[8],"practical":[9],"deployment":[10],"remains":[11],"hindered":[12],"by":[13,179,191],"two":[14],"key":[15],"limitations:":[16],"**1)":[17],"perceptual":[18],"redundancy**,":[19],"where":[20],"irrelevant":[21],"visual":[22],"inputs":[23],"are":[24],"processed":[25],"inefficiently,":[26],"and":[27,52,81,103,116,121,147,158,171,188,193],"**2)":[28],"superficial":[29],"instruction-vision":[30],"alignment**,":[31],"which":[32],"hampers":[33],"semantic":[34,66,83],"grounding":[35],"of":[36],"actions.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"**SemanticVLA**,":[43],"a":[44,165],"novel":[45],"VLA":[46],"framework":[47],"that":[48,162],"performs":[49],"Semantic-Aligned":[50],"Sparsification":[51],"Enhancement":[53],"for":[54,123,151],"Efficient":[55],"Robotic":[56],"Manipulation.":[57],"Specifically:":[58],"**1)**":[59],"To":[60,99,127],"sparsify":[61],"redundant":[62],"perception":[63,132],"while":[64,184],"preserving":[65],"alignment,":[67],"**Semantic-guided":[68],"Dual":[69],"Visual":[70],"Pruner":[71,75,88],"(SD-Pruner)**":[72],"performs:":[73],"Instruction-driven":[74],"(ID-Pruner)":[76],"extracts":[77],"global":[78],"action":[79],"cues":[80],"local":[82],"anchors":[84],"SigLIP;":[86],"Spatial-aggregation":[87],"(SA-Pruner)":[89],"compacts":[90],"geometry-rich":[91],"features":[92,102],"into":[93],"task-adaptive":[94],"tokens":[95,118],"DINOv2.":[97],"**2)**":[98],"exploit":[100],"sparsified":[101],"integrate":[104],"semantics":[105],"with":[106],"spatial":[107],"geometry,":[108],"**Semantic-complementary":[109],"Hierarchical":[110],"Fuser":[111],"(SH-Fuser)**":[112],"fuses":[113],"dense":[114],"patches":[115],"sparse":[117],"across":[119],"SigLIP":[120],"DINOv2":[122],"coherent":[124],"representation.":[125],"**3)**":[126],"enhance":[128],"the":[129,140],"transformation":[130],"from":[131],"to":[133],"action,":[134],"**Semantic-conditioned":[135],"Action":[136],"Coupler":[137],"(SA-Coupler)**":[138],"replaces":[139],"conventional":[141],"observation-to-DoF":[142],"approach,":[143],"yielding":[144],"more":[145],"efficient":[146],"interpretable":[148],"behavior":[149],"modeling":[150],"manipulation":[152],"tasks.":[153],"Extensive":[154],"experiments":[155],"on":[156,176],"simulation":[157],"real-world":[159],"tasks":[160],"show":[161],"SemanticVLA":[163,173],"sets":[164],"new":[166],"SOTA":[167],"both":[169],"performance":[170],"efficiency.":[172],"surpasses":[174],"OpenVLA":[175],"LIBERO":[177],"benchmark":[178],"**21.1%**":[180],"success":[182],"rate,":[183],"reducing":[185],"training":[186],"cost":[187],"inference":[189],"latency":[190],"**3.0\u00d7**":[192],"**2.7\u00d7**.":[194]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}