{"id":"https://openalex.org/W7160076956","doi":"https://doi.org/10.1109/iccv51701.2025.00917","title":"IRASim: A Fine-Grained World Model for Robot Manipulation","display_name":"IRASim: A Fine-Grained World Model for Robot Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7160076956","doi":"https://doi.org/10.1109/iccv51701.2025.00917"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","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/A5135236375","display_name":"Fangqi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fangqi Zhu","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135202663","display_name":"Hongtao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Hongtao Wu","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135124725","display_name":"Song Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Song Guo","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069814200","display_name":"Y Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Yuxiao Liu","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071789313","display_name":"Chilam Cheang","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Chilam Cheang","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135142079","display_name":"Tao Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tao Kong","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.65662119,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9834","last_page":"9844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.34389999508857727,"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":0.34389999508857727,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.08659999817609787,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.05490000173449516,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/robot","display_name":"Robot","score":0.5425000190734863},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3100000023841858},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.296999990940094},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.28600001335144043},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.28450000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5709999799728394},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2858999967575073},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.28450000286102295},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.25949999690055847}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.00917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-171234","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-171234","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4420928657054901,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2064076387","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2528489519","https://openalex.org/W4252189904","https://openalex.org/W4385403811","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4386071831","https://openalex.org/W4390872297","https://openalex.org/W4391759936","https://openalex.org/W4402354046","https://openalex.org/W4402704510","https://openalex.org/W4415796676","https://openalex.org/W7103752023","https://openalex.org/W7133218093","https://openalex.org/W7133220882"],"related_works":[],"abstract_inverted_index":{"World":[0],"models":[1],"allow":[2],"autonomous":[3],"agents":[4],"to":[5,24,92,146,178,192],"plan":[6],"and":[7,45,72,81,95,119,126,202],"explore":[8],"by":[9,111,165],"predicting":[10],"the":[11,27,32,46,97,105,108,116,140,169,173],"visual":[12,33],"outcomes":[13],"of":[14,60,107],"different":[15],"actions.":[16],"However,":[17],"for":[18],"robot":[19,73],"manipulation,":[20],"it":[21],"is":[22],"challenging":[23],"accurately":[25],"model":[26,58,94,124],"fine-grained":[28,64],"robot-object":[29],"interaction":[30,66],"within":[31,88],"space":[34],"using":[35,131,139],"existing":[36],"methods":[37,118],"which":[38],"overlooks":[39],"precise":[40],"alignment":[41],"between":[42],"each":[43,89],"action":[44,74,184],"corresponding":[47],"frame.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"present":[53],"IRASim,":[54],"a":[55,78,83,134,196],"novel":[56,84],"world":[57],"capable":[59],"generating":[61],"videos":[62,109],"with":[63,122,137,157],"robotobject":[65],"details,":[67],"conditioned":[68],"on":[69,172],"historical":[70],"observations":[71],"trajectories.":[75],"We":[76],"train":[77],"diffusion":[79],"transformer":[80,90],"introduce":[82],"frame-level":[85],"actionconditioning":[86],"module":[87],"block":[91],"explicitly":[93],"strengthen":[96],"action-frame":[98],"alignment.":[99],"Extensive":[100],"experiments":[101],"show":[102],"that:":[103],"(1)":[104],"quality":[106],"generated":[110],"our":[112],"method":[113],"surpasses":[114],"all":[115],"baseline":[117],"scales":[120],"effectively":[121],"increased":[123],"size":[125],"computation;":[127],"(2)":[128],"policy":[129,149,161],"evaluations":[130],"IRASim":[132,158,181],"exhibit":[133],"strong":[135],"correlation":[136],"those":[138],"ground-truth":[141],"simulator,":[142],"highlighting":[143],"its":[144],"potential":[145],"accelerate":[147],"real-world":[148],"evaluation;":[150],"(3)":[151],"testing-time":[152],"scaling":[153],"through":[154],"model-based":[155],"planning":[156],"significantly":[159],"enhances":[160],"performance,":[162],"as":[163],"evidenced":[164],"an":[166],"improvement":[167],"in":[168,190],"IoU":[170],"metric":[171],"Push-T":[174],"benchmark":[175],"from":[176],"0.637":[177],"0.961;":[179],"(4)":[180],"provides":[182],"flexible":[183],"controllability,":[185],"allowing":[186],"virtual":[187],"robotic":[188],"arms":[189],"datasets":[191],"be":[193],"controlled":[194],"via":[195],"keyboard":[197],"or":[198],"VR":[199],"controller.":[200],"Video":[201],"code":[203],"are":[204],"available":[205],"at":[206],"https://gen-irasim.github.io/.<br/>":[207]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-05-05T00:00:00"}