{"id":"https://openalex.org/W4416749473","doi":"https://doi.org/10.1109/iros60139.2025.11245844","title":"Stimulating Imagination: Towards General-purpose \"Something Something Placement\"","display_name":"Stimulating Imagination: Towards General-purpose \"Something Something Placement\"","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749473","doi":"https://doi.org/10.1109/iros60139.2025.11245844"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074471394","display_name":"Jianyang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianyang Wu","raw_affiliation_strings":["Rightly Robotics,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Rightly Robotics,Hangzhou,China","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100301877","display_name":"Gu Jie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Gu","raw_affiliation_strings":["Rightly Robotics,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Rightly Robotics,Hangzhou,China","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045699018","display_name":"Xiaolei Ma","orcid":"https://orcid.org/0000-0002-3841-5792"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaokang Ma","raw_affiliation_strings":["Rightly Robotics,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Rightly Robotics,Hangzhou,China","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120386284","display_name":"Fangzhou Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fangzhou Qiu","raw_affiliation_strings":["Rightly Robotics,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Rightly Robotics,Hangzhou,China","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102219351","display_name":"Tang Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chu Tang","raw_affiliation_strings":["Rightly Robotics,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Rightly Robotics,Hangzhou,China","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450174","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0002-2362-5359"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingmin Chen","raw_affiliation_strings":["Rightly Robotics,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Rightly Robotics,Hangzhou,China","institution_ids":["https://openalex.org/I4210116723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5074471394"],"corresponding_institution_ids":["https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48322985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"701","last_page":"707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7764999866485596,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7764999866485596,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.050700001418590546,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.025100000202655792,"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/leverage","display_name":"Leverage (statistics)","score":0.7278000116348267},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6437000036239624},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.524399995803833},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5120000243186951},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4767000079154968},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4496000111103058},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.42590001225471497},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4131999909877777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7315999865531921},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7278000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6751000285148621},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6437000036239624},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5120000243186951},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4496000111103058},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43220001459121704},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3977000117301941},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3871999979019165},{"id":"https://openalex.org/C17511633","wikidata":"https://www.wikidata.org/wiki/Q830694","display_name":"SMT placement equipment","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C2779542340","wikidata":"https://www.wikidata.org/wiki/Q1062461","display_name":"Learning object","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1932888261","https://openalex.org/W3035198432","https://openalex.org/W3091332498","https://openalex.org/W3111535274","https://openalex.org/W3130982809","https://openalex.org/W3206916018","https://openalex.org/W3207626483","https://openalex.org/W4285102264","https://openalex.org/W4312424618","https://openalex.org/W4312614111","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4385403811","https://openalex.org/W4385403813","https://openalex.org/W4385403849","https://openalex.org/W4385430538","https://openalex.org/W4386076215","https://openalex.org/W4390873054","https://openalex.org/W4390874575","https://openalex.org/W4401415110","https://openalex.org/W4402670239","https://openalex.org/W4402754134","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"General-purpose":[0],"object":[1,32,49,89,116,139],"placement":[2,33],"is":[3,27,105,124,155,162,172],"a":[4,58,64,77],"fundamental":[5],"capability":[6],"of":[7,14,114,186],"an":[8],"intelligent":[9],"generalist":[10],"robot:":[11],"being":[12],"capable":[13],"rearranging":[15],"objects":[16],"following":[17],"precise":[18],"human":[19],"instructions":[20],"even":[21],"in":[22,85,174],"novel":[23],"environments.":[24],"This":[25],"work":[26],"dedicated":[28],"to":[29,81,136,207],"achieving":[30],"general-purpose":[31],"with":[34],"\"something":[35],"something\"":[36],"instructions.":[37],"Specifically,":[38],"we":[39,107],"break":[40],"the":[41,111,127,131,138,142,152,168,184],"entire":[42],"process":[43],"down":[44],"into":[45],"three":[46],"parts,":[47,99],"including":[48],"localization,":[50],"goal":[51,169,196],"imagination":[52],"and":[53,56,75,118,158,176],"robot":[54],"control,":[55],"propose":[57],"method":[59],"named":[60],"SPORT.":[61],"SPORT":[62,189],"leverages":[63],"pre-trained":[65],"large":[66],"vision":[67],"model":[68],"for":[69,126,147,167,198],"broad":[70],"semantic":[71,149],"reasoning":[72],"about":[73],"objects,":[74,201],"learns":[76],"diffusion-based":[78,132],"pose":[79,170],"estimator":[80,133],"ensure":[82],"physically-realistic":[83],"results":[84,182],"3D":[86,195],"space.":[87],"Only":[88],"types":[90],"(movable":[91],"or":[92],"reference)":[93],"are":[94],"communicated":[95],"between":[96],"these":[97],"two":[98,102],"which":[100],"brings":[101],"benefits.":[103],"One":[104],"that":[106],"can":[108,190],"fully":[109],"leverage":[110],"powerful":[112],"ability":[113],"open-set":[115],"recognition":[117],"localization":[119],"since":[120],"no":[121,145,159],"specific":[122],"fine-tuning":[123],"needed":[125],"robotic":[128],"scenario.":[129],"Moreover,":[130],"only":[134,192],"need":[135],"\"imagine\"":[137],"poses":[140,197],"after":[141],"placement,":[143],"while":[144],"necessity":[146],"their":[148],"information.":[150],"Thus":[151],"training":[153,161,165],"burden":[154],"greatly":[156],"reduced":[157],"massive":[160],"required.":[163],"The":[164],"data":[166],"estimation":[171],"collected":[173],"simulation":[175],"annotated":[177],"by":[178],"using":[179],"GPT-4.":[180],"Experimental":[181],"demonstrate":[183],"effectiveness":[185],"our":[187],"approach.":[188],"not":[191],"generate":[193],"promising":[194],"unseen":[199],"simulated":[200],"but":[202],"also":[203],"be":[204],"seamlessly":[205],"applied":[206],"real-world":[208],"settings.":[209]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}