{"id":"https://openalex.org/W7134269524","doi":"https://doi.org/10.48550/arxiv.2603.06480","title":"History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation","display_name":"History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7134269524","doi":"https://doi.org/10.48550/arxiv.2603.06480"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.06480","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128522002","display_name":"Qitong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011708638","display_name":"Yijun Liang","orcid":"https://orcid.org/0000-0002-6373-3944"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Yijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128382559","display_name":"Ming Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128537189","display_name":"Tianyi Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Tianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005424498","display_name":"Christopher Rasmussen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rasmussen, Christopher","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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29894603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9660000205039978,"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":0.9660000205039978,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.005499999970197678,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0038999998942017555,"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":0.6456000208854675},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.628000020980835},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5582000017166138},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5454999804496765},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4812000095844269},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.43720000982284546},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43650001287460327},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4077000021934509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.628000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5663999915122986},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5582000017166138},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.43720000982284546},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3440999984741211},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.3158000111579895},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.31439998745918274},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2653000056743622}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.06480","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.06480","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.06480","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.06480","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"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":[0],"Navigation":[1],"(VLN)":[2],"enables":[3],"robots":[4],"to":[5,52,60],"follow":[6],"natural-language":[7],"instructions":[8],"in":[9,175],"visually":[10],"grounded":[11],"environments,":[12],"serving":[13],"as":[14],"a":[15,44,142],"key":[16],"capability":[17],"for":[18,67],"embodied":[19,173],"robotic":[20,156,176],"systems.":[21,104,178],"Recent":[22],"Vision-Language-Action":[23],"(VLA)":[24],"models":[25],"have":[26],"demonstrated":[27],"strong":[28],"navigation":[29,125,153,177],"performance,":[30],"but":[31],"their":[32],"high":[33],"computational":[34],"cost":[35],"introduces":[36],"latency":[37],"that":[38,113],"limits":[39],"real-time":[40,172],"deployment.":[41],"We":[42,55,158],"propose":[43],"training-free":[45],"spatio-temporal":[46,65,84],"vision":[47],"token":[48,58,80],"pruning":[49,119,129],"framework":[50],"tailored":[51],"VLA-based":[53],"VLN.":[54],"apply":[56],"spatial":[57],"selection":[59],"the":[61,86,134,164],"current":[62],"view,":[63],"alongside":[64],"compression":[66],"historical":[68],"memories,":[69],"enabling":[70],"efficient":[71],"long-horizon":[72],"inference":[73,137],"while":[74,132],"reducing":[75],"redundant":[76],"computation.":[77],"Leveraging":[78],"attention-based":[79],"importance":[81],"and":[82,150,170],"query-guided":[83],"filtering,":[85],"proposed":[87],"approach":[88],"preserves":[89,123],"navigation-relevant":[90],"information":[91],"without":[92],"retraining":[93],"or":[94],"modifying":[95],"pretrained":[96],"models,":[97],"allowing":[98],"plug-and-play":[99],"integration":[100],"into":[101],"existing":[102,118],"VLA":[103],"Through":[105],"experiments":[106],"on":[107,141],"standard":[108],"VLN":[109],"benchmarks,":[110],"we":[111],"confirm":[112],"our":[114],"method":[115],"significantly":[116],"outperforms":[117],"strategies.":[120],"It":[121],"successfully":[122],"superior":[124],"accuracy":[126],"under":[127,154],"extreme":[128],"scenarios,":[130],"all":[131],"maintaining":[133],"highly":[135],"competitive":[136],"efficiency.":[138],"Real-world":[139],"deployment":[140,174],"Unitree":[143],"Go2":[144],"quadruped":[145],"robot":[146],"further":[147],"validates":[148],"reliable":[149],"low-latency":[151],"instruction-following":[152],"practical":[155],"constraints.":[157],"hope":[159],"this":[160],"work":[161],"helps":[162],"bridge":[163],"gap":[165],"between":[166],"large-scale":[167],"multimodal":[168],"modeling":[169],"efficient,":[171],"Project":[179],"Page:":[180],"https://wqtwjt1996.github.io/publications/2026-vln.html":[181]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-10T00:00:00"}