{"id":"https://openalex.org/W7123477539","doi":"https://doi.org/10.48550/arxiv.2601.06474","title":"SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and Planning","display_name":"SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and Planning","publication_year":2026,"publication_date":"2026-01-10","ids":{"openalex":"https://openalex.org/W7123477539","doi":"https://doi.org/10.48550/arxiv.2601.06474"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.06474","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.06474","pdf_url":"https://arxiv.org/pdf/2601.06474","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.06474","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122918021","display_name":"Chenxu Dang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dang, Chenxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122951528","display_name":"Jie Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jie","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126815848","display_name":"Guang Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Guang","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150965860","display_name":"Zhiwen Hou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hou, Zhiwen","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122970647","display_name":"Zihan You","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You, Zihan","raw_affiliation_strings":["Institute for AI Industry Research (AIR) , Tsinghua University https :// msundyy "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR) , Tsinghua University https :// msundyy ","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080844671","display_name":"Hangjun Ye","orcid":"https://orcid.org/0009-0001-9570-7927","observed_orcids":["https://orcid.org/0009-0001-9570-7927"]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Hangjun","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122948736","display_name":"Jie Ma","orcid":"https://orcid.org/0009-0007-9967-867X","observed_orcids":["https://orcid.org/0009-0007-9967-867X"]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Jie","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126827349","display_name":"Long Chen","orcid":"https://orcid.org/0000-0002-4985-9516","observed_orcids":["https://orcid.org/0000-0002-4985-9516"]},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Long","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159810500","display_name":"Yan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yan","raw_affiliation_strings":["Institute for AI Industry Research (AIR) , Tsinghua University https :// msundyy "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR) , Tsinghua University https :// msundyy ","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.5806000232696533,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.5806000232696533,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18320000171661377,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.03929999843239784,"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/vision-language-action-models","display_name":"vision-language-action models","score":0.8460000157356262},{"id":"https://openalex.org/keywords/occupancy-forecasting","display_name":"occupancy forecasting","score":0.8600000143051147},{"id":"https://openalex.org/keywords/trajectory-planning","display_name":"trajectory planning","score":0.7559999823570251},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.9380000233650208},{"id":"https://openalex.org/keywords/scene-understanding","display_name":"scene understanding","score":0.656000018119812}],"concepts":[{"id":"https://openalex.org/C160331591","wikidata":"https://www.wikidata.org/wiki/Q7075743","display_name":"Occupancy","level":2,"score":0.8917999863624573},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8062999844551086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7325000166893005},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5163999795913696},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.445499986410141},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.413100004196167},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37400001287460327},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C57077369","wikidata":"https://www.wikidata.org/wiki/Q7075747","display_name":"Occupancy grid mapping","level":4,"score":0.290800005197525},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.06474","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.06474","pdf_url":"https://arxiv.org/pdf/2601.06474","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2601.06474","doi":"https://doi.org/10.48550/arxiv.2601.06474","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.06474","pdf_url":null,"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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.06474","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.06474","pdf_url":"https://arxiv.org/pdf/2601.06474","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7123477539.pdf","grobid_xml":"https://content.openalex.org/works/W7123477539.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W3092442149","https://openalex.org/W4388927584","https://openalex.org/W4391988276","https://openalex.org/W4403556110","https://openalex.org/W4403570669","https://openalex.org/W4403853618","https://openalex.org/W4404341829","https://openalex.org/W4406841381","https://openalex.org/W4407424328","https://openalex.org/W4413925291","https://openalex.org/W4414565400","https://openalex.org/W4415059311","https://openalex.org/W4416014922","https://openalex.org/W4416413108","https://openalex.org/W4416749753","https://openalex.org/W7108482493","https://openalex.org/W7137982449","https://openalex.org/W7160091217","https://openalex.org/W7160197198","https://openalex.org/W7196963124","https://openalex.org/W7201855872"],"related_works":["https://openalex.org/W4415059311","https://openalex.org/W4403556110","https://openalex.org/W4413513669","https://openalex.org/W6891932074","https://openalex.org/W7169226898","https://openalex.org/W7165368359","https://openalex.org/W7133555807","https://openalex.org/W7223057973","https://openalex.org/W7165383424","https://openalex.org/W4417452301"],"abstract_inverted_index":{"In":[0],"autonomous":[1],"driving,":[2],"Vision":[3],"Language":[4],"Models":[5],"(VLMs)":[6],"excel":[7],"at":[8],"high-level":[9],"reasoning":[10],",":[11],"whereas":[12],"semantic":[13,46],"occupancy":[14,47,86,94,110,141],"provides":[15,48],"fine-grained":[16],"details.":[17],"Despite":[18],"significant":[19],"progress":[20],"in":[21,168,178],"individual":[22],"fields,":[23],"there":[24],"is":[25,55],"still":[26],"no":[27],"method":[28],"that":[29,82,112],"can":[30],"effectively":[31],"integrate":[32,59],"both":[33],"paradigms.":[34],"Conventional":[35],"VLMs":[36,72],"struggle":[37],"with":[38,61,97],"token":[39],"explosion":[40],"and":[41,67,73,88,120,130,139,154,183],"limited":[42],"spatiotemporal":[43],"reasoning,":[44],"while":[45],"a":[49,78,98,164,175],"unified,":[50],"explicit":[51],"spatial":[52],"representation":[53],"but":[54],"too":[56],"dense":[57],"to":[58],"efficiently":[60],"VLMs.":[62],"To":[63],"address":[64],"these":[65],"challenges":[66],"bridge":[68,117],"the":[69,115,127,133,171],"gap":[70],"between":[71,118],"occupancy,":[74],"we":[75,144],"propose":[76],"SparseOccVLA,":[77],"novel":[79],"vision-language-action":[80],"model":[81],"unifies":[83],"scene":[84,137],"understanding,":[85],"forecasting,":[87],"trajectory":[89],"planning":[90,187],"powered":[91],"by":[92,132],"sparse":[93,109],"queries.":[95],"Starting":[96],"lightweight":[99],"Sparse":[100],"Occupancy":[101],"Encoder,":[102],"SparseOccVLA":[103,162],"generates":[104],"compact":[105],"yet":[106],"highly":[107],"informative":[108],"queries":[111,123],"serve":[113],"as":[114,156,158],"single":[116],"vision":[119],"language.":[121],"These":[122],"are":[124],"aligned":[125],"into":[126],"language":[128],"space":[129],"reasoned":[131],"LLM":[134],"for":[135],"unified":[136],"understanding":[138],"future":[140],"forecasting.":[142],"Furthermore,":[143],"introduce":[145],"an":[146],"LLM-guided":[147],"Anchor-Diffusion":[148],"Planner":[149],"featuring":[150],"decoupled":[151],"anchor":[152],"scoring":[153],"denoising,":[155],"well":[157],"cross-model":[159],"trajectory-condition":[160],"fusion.":[161],"achieves":[163],"7%":[165],"relative":[166],"improvement":[167],"CIDEr":[169],"over":[170],"state-of-the-art":[172,185],"on":[173,181,189],"OmniDrive-nuScenes,":[174],"0.5":[176],"increase":[177],"mIoU":[179],"score":[180],"Occ3D-nuScenes,":[182],"sets":[184],"open-loop":[186],"metric":[188],"nuScenes":[190],"benchmark,":[191],"demonstrating":[192],"its":[193],"strong":[194],"holistic":[195],"capability.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-01-14T00:00:00"}