{"id":"https://openalex.org/W7166650853","doi":"https://doi.org/10.48550/arxiv.2606.28758","title":"X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving","display_name":"X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving","publication_year":2026,"publication_date":"2026-06-27","ids":{"openalex":"https://openalex.org/W7166650853","doi":"https://doi.org/10.48550/arxiv.2606.28758"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.28758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28758","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.28758","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139674653","display_name":"Bohao Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Bohao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101375736","display_name":"Chengrui Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Chengrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139686151","display_name":"Guangfeng Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Guangfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139646588","display_name":"Ruixin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ruixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139689741","display_name":"Xuejie Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Xuejie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137285075","display_name":"LIU Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053102287","display_name":"Sutao Deng","orcid":"https://orcid.org/0000-0002-8984-516X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Sutao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055820653","display_name":"Xiuyang Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Xiuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139651328","display_name":"Pengkun Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Pengkun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139713527","display_name":"Jinyun Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jinyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139696237","display_name":"Rui Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071582484","display_name":"Hanpeng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hanpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111013520","display_name":"Yutong Zheng","orcid":"https://orcid.org/0009-0005-8946-9132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Yutong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101893660","display_name":"Yi Guo","orcid":"https://orcid.org/0009-0006-1890-6726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100560806","display_name":"Xinlong Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Xinlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025168836","display_name":"Qingyu Luo","orcid":"https://orcid.org/0000-0002-1980-4725"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Qingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078754732","display_name":"Zhuangzhuang Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Zhuangzhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139665792","display_name":"Yu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139701031","display_name":"Hang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139709640","display_name":"Xianming Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xianming","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":null,"has_fulltext":false,"cited_by_count":0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5360000133514404,"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":0.5360000133514404,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.20360000431537628,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.050599999725818634,"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/sketch","display_name":"Sketch","score":0.7840999960899353},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5213000178337097},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46380001306533813},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.46140000224113464},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.42500001192092896},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4235000014305115},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.367000013589859},{"id":"https://openalex.org/keywords/advanced-driver-assistance-systems","display_name":"Advanced driver assistance systems","score":0.34540000557899475}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7840999960899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318999767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5771999955177307},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46380001306533813},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.46140000224113464},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.42500001192092896},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C151927369","wikidata":"https://www.wikidata.org/wiki/Q1981312","display_name":"Neuromorphic engineering","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.28758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28758","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":"doi:10.48550/arxiv.2606.28758","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28758","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Predicting":[0],"future":[1,96,114,165,186],"states":[2],"is":[3,92,104,123,188],"essential":[4],"for":[5],"autonomous":[6],"agents,":[7],"yet":[8],"current":[9],"Vision-Language-Action":[10],"(VLA)":[11],"models":[12,55],"fundamentally":[13],"lack":[14],"this":[15,30,57,72,171],"capability,":[16,59],"relying":[17],"instead":[18],"on":[19,129,236],"reactive":[20],"perception-action":[21],"mapping.":[22],"While":[23],"integrating":[24],"Predictive":[25],"World":[26],"Models":[27],"(PWMs)":[28],"addresses":[29],"gap,":[31],"existing":[32],"approaches":[33],"either":[34],"incur":[35],"prohibitive":[36],"cascaded":[37],"latency":[38],"or":[39],"act":[40],"as":[41,67,76,173],"shallow":[42],"terminal":[43],"tasks":[44],"that":[45,103,144,211,254],"fail":[46],"to":[47,88,94,190,200],"deeply":[48],"embed":[49],"forward-looking":[50],"reasoning.":[51],"To":[52],"endow":[53],"VLA":[54],"with":[56,150],"reasoning":[58,259],"we":[60,126,133,204],"propose":[61,205],"X-Mind.":[62],"Rather":[63,160],"than":[64,161],"treating":[65],"PWMs":[66],"an":[68,141],"external":[69],"auxiliary":[70],"module,":[71],"framework":[73],"internalizes":[74],"them":[75],"the":[77,90,113,167,195,213,217,220,228],"Visual":[78],"Chain-of-Thought":[79],"(Visual":[80],"CoT).":[81],"By":[82],"enforcing":[83],"a":[84,100,135,146,174,179,184,206,249],"world":[85],"rollout":[86,187],"prior":[87],"action,":[89],"model":[91,168],"constrained":[93],"imagine":[95],"evolution":[97],"first,":[98],"yielding":[99],"driving":[101,152,244],"policy":[102],"robustly":[105],"grounded":[106],"in":[107],"environmental":[108],"dynamics":[109],"and":[110,125,157,234],"aware":[111],"of":[112,138,219],"consequences":[115],"its":[116],"actions":[117],"will":[118],"unfold.":[119],"The":[120],"challenge":[121],"here":[122],"efficiency,":[124],"tackle":[127],"it":[128,248],"two":[130],"fronts.":[131],"First,":[132],"introduce":[134],"compact":[136],"representation":[137],"visual":[139],"thinking:":[140],"abstract":[142,151],"sketch":[143,172],"fuses":[145],"Bird's-Eye-View":[147],"(BEV)":[148],"layout":[149],"priors":[153],"(e.g.,":[154],"navigation":[155],"intents":[156],"traffic":[158],"rules).":[159],"rolling":[162],"out":[163],"dense":[164],"frames,":[166],"reasons":[169],"over":[170],"mental":[175],"canvas;":[176],"aided":[177],"by":[178],"Deep":[180],"Compression":[181],"Autoencoder":[182],"(DC-AE),":[183],"12-frame":[185],"reduced":[189],"merely":[191],"96":[192],"tokens,":[193],"alleviating":[194],"long-context":[196],"computational":[197],"bottleneck.":[198],"Second,":[199],"accelerate":[201],"generation":[202],"further,":[203],"recurrent":[207],"block":[208],"diffusion":[209],"scheme":[210],"unrolls":[212],"denoising":[214],"steps":[215],"across":[216],"layers":[218],"large":[221],"drive":[222],"model,":[223],"folding":[224],"iterative":[225],"refinement":[226],"into":[227],"backbone's":[229],"one":[230],"forward":[231],"pass.":[232],"Trained":[233],"validated":[235],"large-scale":[237,257],"real-world":[238],"data,":[239],"X-Mind":[240],"achieves":[241],"competitive":[242],"end-to-end":[243],"performance,":[245],"which":[246],"makes":[247],"highly":[250],"practical,":[251],"low-latency":[252],"solution":[253],"successfully":[255],"deploys":[256],"cognitive":[258],"directly":[260],"onto":[261],"resource-constrained":[262],"vehicle":[263],"platforms.":[264]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}