{"id":"https://openalex.org/W7083686993","doi":"https://doi.org/10.48550/arxiv.2509.22652","title":"Pixel Motion Diffusion is What We Need for Robot Control","display_name":"Pixel Motion Diffusion is What We Need for Robot Control","publication_year":2025,"publication_date":"2025-09-26","ids":{"openalex":"https://openalex.org/W7083686993","doi":"https://doi.org/10.48550/arxiv.2509.22652"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2509.22652","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.22652","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2509.22652","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nguyen, E-Ro","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nguyen, E-Ro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Yichi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yichi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ranasinghe, Kanchana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ranasinghe, Kanchana","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Xiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Ryoo, Michael S.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryoo, Michael S.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6491000056266785,"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"}},"topics":[{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6491000056266785,"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"}},{"id":"https://openalex.org/T13067","display_name":"Geological Modeling and Analysis","score":0.02370000071823597,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.021400000900030136,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.680400013923645},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6305000185966492},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5098000168800354},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.46070000529289246},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4562999904155731},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4296000003814697},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.39640000462532043}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6998999714851379},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.680400013923645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.677299976348877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6308000087738037},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6305000185966492},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.37540000677108765},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.36070001125335693},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.2773999869823456},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2509.22652","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.22652","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2509.22652","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.22652","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":"article"},"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":{"We":[0,6],"present":[1],"DAWN":[2,57],"(Diffusion":[3],"is":[4],"All":[5],"Need":[7],"for":[8,15,107,126],"robot":[9,26,130],"control),":[10],"a":[11,47,123],"unified":[12],"diffusion-based":[13,104],"framework":[14],"language-conditioned":[16],"robotic":[17,108],"manipulation":[18],"that":[19],"bridges":[20],"high-level":[21,37],"motion":[22,31,55,105],"intent":[23],"and":[24,38,70,84,86,128],"low-level":[25,39],"action":[27],"via":[28],"structured":[29],"pixel":[30],"representation.":[32],"In":[33],"DAWN,":[34],"both":[35],"the":[36,62,78,100,113],"controllers":[40],"are":[41],"modeled":[42],"as":[43,122],"diffusion":[44,117],"processes,":[45],"yielding":[46],"fully":[48],"trainable,":[49],"end-to-end":[50],"system":[51],"with":[52,95,119],"interpretable":[53],"intermediate":[54],"abstractions.":[56],"achieves":[58],"state-of-the-art":[59],"results":[60,111],"on":[61,75],"challenging":[63],"CALVIN":[64],"benchmark,":[65],"demonstrating":[66],"strong":[67,124],"multi-task":[68],"performance,":[69],"further":[71],"validates":[72],"its":[73],"effectiveness":[74,114],"MetaWorld.":[76],"Despite":[77],"substantial":[79],"domain":[80],"gap":[81],"between":[82],"simulation":[83],"reality":[85],"limited":[87],"real-world":[88,93],"data,":[89],"we":[90],"demonstrate":[91],"reliable":[92],"transfer":[94],"only":[96],"minimal":[97],"finetuning,":[98],"illustrating":[99],"practical":[101],"viability":[102],"of":[103,115],"abstractions":[106],"control.":[109],"Our":[110],"show":[112],"combining":[116],"modeling":[118],"motion-centric":[120],"representations":[121],"baseline":[125],"scalable":[127],"robust":[129],"learning.":[131],"Project":[132],"page:":[133],"https://eronguyen.github.io/DAWN/":[134]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-10-10T00:00:00"}