{"id":"https://openalex.org/W4410636363","doi":"https://doi.org/10.1145/3701716.3717565","title":"CubeRobot: Grounding Language in Rubik's Cube Manipulation via Vision-Language Model","display_name":"CubeRobot: Grounding Language in Rubik's Cube Manipulation via Vision-Language Model","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636363","doi":"https://doi.org/10.1145/3701716.3717565"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3717565","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717565","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717565","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717565","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087312033","display_name":"Feiyang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feiyang Wang","raw_affiliation_strings":["Central South University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101922655","display_name":"Xiaomin Yu","orcid":"https://orcid.org/0000-0003-4846-3162"},"institutions":[{"id":"https://openalex.org/I4396570619","display_name":"Great Bay University","ror":"https://ror.org/01hdgge16","country_code":null,"type":"education","lineage":["https://openalex.org/I4396570619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomin Yu","raw_affiliation_strings":["Great Bay University, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Great Bay University, Guangdong, China","institution_ids":["https://openalex.org/I4396570619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003207136","display_name":"Wangyu Wu","orcid":"https://orcid.org/0009-0005-8404-9489"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wangyu Wu","raw_affiliation_strings":["The University of Liverpool, Liverpool, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The University of Liverpool, Liverpool, United Kingdom","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087312033"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":3.6542,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92941368,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2181","last_page":"2186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9923999905586243,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9837999939918518,"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/cube","display_name":"Cube (algebra)","score":0.7189186215400696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6999416351318359},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6153404712677002},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5501322746276855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5310300588607788},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4994843006134033},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.42205607891082764},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.39165154099464417},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3230556845664978},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1366960108280182},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12560462951660156},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12381482124328613},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.0944209098815918}],"concepts":[{"id":"https://openalex.org/C53051483","wikidata":"https://www.wikidata.org/wiki/Q861555","display_name":"Cube (algebra)","level":2,"score":0.7189186215400696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6999416351318359},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6153404712677002},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5501322746276855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310300588607788},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4994843006134033},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.42205607891082764},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.39165154099464417},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3230556845664978},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1366960108280182},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12560462951660156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12381482124328613},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0944209098815918}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3717565","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717565","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717565","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3717565","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717565","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717565","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636363.pdf","grobid_xml":"https://content.openalex.org/works/W4410636363.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2593463961","https://openalex.org/W3177174258","https://openalex.org/W4226278401","https://openalex.org/W4287113019","https://openalex.org/W4293518965","https://openalex.org/W4312605942","https://openalex.org/W4365799947","https://openalex.org/W4386336922","https://openalex.org/W4390873070","https://openalex.org/W4391948751","https://openalex.org/W4392797070","https://openalex.org/W4401308301","https://openalex.org/W4401687172","https://openalex.org/W4402916798","https://openalex.org/W4403792044","https://openalex.org/W4404459638","https://openalex.org/W4406110380","https://openalex.org/W4406461639","https://openalex.org/W4406612399","https://openalex.org/W6600008909","https://openalex.org/W6600103761","https://openalex.org/W6600213211","https://openalex.org/W6601010567"],"related_works":["https://openalex.org/W2021787609","https://openalex.org/W1537063595","https://openalex.org/W4405810791","https://openalex.org/W2097328689","https://openalex.org/W4234899305","https://openalex.org/W4283690284","https://openalex.org/W2379604501","https://openalex.org/W3180808905","https://openalex.org/W2405444689","https://openalex.org/W2373854414"],"abstract_inverted_index":{"Proving":[0],"Rubik's":[1,22,58,127,133],"Cube":[2,23,128,134],"theorems":[3],"at":[4],"the":[5,71],"high":[6,140],"level":[7],"represents":[8],"a":[9,49,95,102,139],"notable":[10],"milestone":[11],"in":[12,81,131,148,158],"human-level":[13],"spatial":[14],"imagination":[15],"and":[16,19,30,39,66,99,120,125,151],"logic":[17],"thinking":[18],"reasoning.":[20],"Traditional":[21],"robots,":[24],"relying":[25],"on":[26],"complex":[27,38],"vision":[28],"systems":[29],"fixed":[31],"algorithms,":[32],"often":[33],"struggle":[34],"to":[35,37,87,115,146],"adapt":[36],"dynamic":[40],"scenarios.":[41],"To":[42],"overcome":[43],"this":[44],"limitation,":[45],"we":[46],"introduce":[47],"CubeRobot,":[48],"novel":[50],"vision-language":[51],"model":[52],"(VLM)":[53],"tailored":[54],"for":[55,104],"solving":[56],"3x3":[57],"Cubes,":[59],"empowering":[60],"embodied":[61],"agents":[62],"with":[63],"multimodal":[64],"understanding":[65],"execution":[67],"capabilities.":[68],"We":[69,93],"used":[70],"CubeCoT":[72],"image":[73],"dataset,":[74],"which":[75],"contains":[76],"multiple-level":[77],"tasks":[78],"(43":[79],"subtasks":[80],"total)":[82],"that":[83],"humans":[84],"are":[85],"unable":[86],"handle,":[88],"encompassing":[89],"various":[90],"cube":[91],"states.":[92],"incorporate":[94],"dual-loop":[96],"VisionCoT":[97],"architecture":[98],"Memory":[100],"Stream,":[101],"paradigm":[103],"extracting":[105],"task-related":[106],"features":[107],"from":[108],"VLM-generated":[109],"planning":[110],"queries,":[111],"thus":[112],"enabling":[113],"CubeRobot":[114,137],"independent":[116],"planning,":[117],"decision-making,":[118],"reflection":[119],"separate":[121],"management":[122],"of":[123,143,156],"high-":[124],"low-level":[126,132],"tasks.":[129,160],"Furthermore,":[130],"restoration":[135],"tasks,":[136,150],"achieved":[138,152],"accuracy":[141,154],"rate":[142,155],"100%,":[144],"similar":[145],"100%":[147],"medium-level":[149],"an":[153],"80%":[157],"high-level":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}