{"id":"https://openalex.org/W7160259254","doi":"https://doi.org/10.48550/arxiv.2605.01581","title":"Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control","display_name":"Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control","publication_year":2026,"publication_date":"2026-05-02","ids":{"openalex":"https://openalex.org/W7160259254","doi":"https://doi.org/10.48550/arxiv.2605.01581"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.01581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01581","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.01581","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135324644","display_name":"Jinhao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Jinhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102964857","display_name":"Zijun Zhou","orcid":"https://orcid.org/0000-0002-7541-4422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zhexuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124326619","display_name":"Huizhe Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Huizhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124352781","display_name":"Yichen Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Yichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124447947","display_name":"Wenlong Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Wenlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135366271","display_name":"Haoming Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Haoming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135376676","display_name":"Youmin Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Youmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135309339","display_name":"Jie Mei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5135324644"],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2667999863624573,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2667999863624573,"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/T10919","display_name":"Neurological disorders and treatments","score":0.18389999866485596,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.17180000245571136,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6330999732017517},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5663999915122986},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5597000122070312},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5548999905586243},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5360999703407288},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.48980000615119934},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.48489999771118164},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4587000012397766}],"concepts":[{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6330999732017517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6262000203132629},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5663999915122986},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5597000122070312},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4867999851703644},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.48489999771118164},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4478999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4226999878883362},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4065999984741211},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2980000078678131},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.2973000109195709},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.01581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01581","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.01581","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01581","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.4807114005088806,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"visuomotor":[1],"policies":[2,152],"perform":[3],"well":[4],"in":[5,36],"robotic":[6],"manipulation,":[7],"yet":[8],"current":[9],"methods":[10],"still":[11],"inherit":[12],"image-generation-style":[13],"decoders":[14],"and":[15,63,122,134,153],"multi-step":[16],"sampling.":[17],"We":[18],"revisit":[19],"this":[20,45,94],"design":[21],"from":[22],"a":[23,37,84,100,106],"frequency-domain":[24],"perspective.":[25],"Robot":[26],"action":[27,81],"trajectories":[28],"are":[29],"highly":[30],"smooth,":[31],"with":[32,105,141],"most":[33],"energy":[34],"concentrated":[35],"few":[38,74],"low-frequency":[39,60],"discrete":[40],"cosine":[41],"transform":[42],"modes.":[43],"Under":[44],"structure,":[46],"we":[47,96],"show":[48],"that":[49,68,80,111],"the":[50,53,59,120,124,146],"error":[51,70],"of":[52,126,145,148],"optimal":[54],"denoiser":[55],"is":[56],"bounded":[57],"by":[58,93],"subspace":[61],"dimension":[62],"residual":[64],"high-frequency":[65],"energy,":[66],"implying":[67],"denoising":[69,82,87],"saturates":[71],"after":[72],"very":[73],"reverse":[75],"steps.":[76],"This":[77],"also":[78],"suggests":[79],"requires":[83],"much":[85],"simpler":[86],"model":[88],"than":[89,143],"image":[90],"generation.":[91],"Motivated":[92],"insight,":[95],"propose":[97],"Hyper-DP3":[98],"(HDP3),":[99],"pocket-scale":[101],"3D":[102,150],"diffusion":[103],"policy":[104],"lightweight":[107],"Diffusion":[108],"Mixer":[109],"decoder":[110],"supports":[112],"two-step":[113,127],"DDIM":[114],"inference.":[115],"Our":[116],"synthetic":[117],"experiments":[118],"validate":[119],"theory":[121],"support":[123],"sufficiency":[125],"denoising.":[128],"Futhermore,":[129],"across":[130],"RoboTwin2.0,":[131],"Adroit,":[132],"MetaWorld,":[133],"real-world":[135],"tasks,":[136],"HDP3":[137],"achieves":[138],"state-of-the-art":[139],"performance":[140],"fewer":[142],"1%":[144],"parameters":[147],"prior":[149],"diffusion-based":[151],"substantially":[154],"lower":[155],"inference":[156],"latency.":[157]},"counts_by_year":[],"updated_date":"2026-06-02T06:17:35.589633","created_date":"2026-05-06T00:00:00"}