{"id":"https://openalex.org/W7202183441","doi":"https://doi.org/10.48550/arxiv.2608.09853","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","display_name":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","publication_year":2026,"publication_date":"2026-08-10","ids":{"openalex":"https://openalex.org/W7202183441","doi":"https://doi.org/10.48550/arxiv.2608.09853"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.09853","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09853","pdf_url":"https://arxiv.org/pdf/2608.09853","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.09853","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104431078","display_name":"Dongchi Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Dongchi","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146452547","display_name":"Hongyin Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hongyin","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146506808","display_name":"Bohan Hou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Bohan","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146576152","display_name":"Siteng Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Siteng","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126780169","display_name":"Zhian Su","orcid":"https://orcid.org/0009-0006-1784-2046","observed_orcids":["https://orcid.org/0009-0006-1784-2046"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Zhian","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146515738","display_name":"Hang Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Hang","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144264088","display_name":"Tong Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Tong","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153559954","display_name":"Jiahao Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jiahao","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005666034","display_name":"Jianfei Yang","orcid":"https://orcid.org/0000-0002-8075-0439","observed_orcids":["https://orcid.org/0000-0002-8075-0439"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jianfei","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146567300","display_name":"Jianfei Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Donglin","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153584866","display_name":"Peixi Peng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Peixi","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153582428","display_name":"Mingxiu Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Mingxiu","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153654568","display_name":"Deli Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Deli","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153590878","display_name":"Xin Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":["Hupan Lab * Equal contribution ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hupan Lab * Equal contribution ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"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":0.9916999936103821,"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":0.9916999936103821,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.007400000002235174,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00019999999494757503,"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/temporal-distance","display_name":"temporal distance","score":0.6959999799728394},{"id":"https://openalex.org/keywords/reward-models","display_name":"reward models","score":0.550000011920929},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.7929999828338623},{"id":"https://openalex.org/keywords/robot-learning","display_name":"robot learning","score":0.5490000247955322},{"id":"https://openalex.org/keywords/behavioral-cloning","display_name":"behavior cloning","score":0.7279999852180481},{"id":"https://openalex.org/keywords/value-guidance","display_name":"value guidance","score":0.5989999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6575000286102295},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6532999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6093999743461609},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5120000243186951},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4408999979496002},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.42640000581741333},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2793999910354614},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.09853","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09853","pdf_url":"https://arxiv.org/pdf/2608.09853","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.09853","doi":"https://doi.org/10.48550/arxiv.2608.09853","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.09853","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.09853","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09853","pdf_url":"https://arxiv.org/pdf/2608.09853","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202183441.pdf","grobid_xml":"https://content.openalex.org/works/W7202183441.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W4414050913","https://openalex.org/W4416684441","https://openalex.org/W4416780398","https://openalex.org/W4417100212","https://openalex.org/W4417299960","https://openalex.org/W7084154250","https://openalex.org/W7106591914","https://openalex.org/W7117676596","https://openalex.org/W7118501563","https://openalex.org/W7129399271","https://openalex.org/W7133361213","https://openalex.org/W7165643088","https://openalex.org/W7204808299"],"related_works":["https://openalex.org/W7165807676","https://openalex.org/W7223029620","https://openalex.org/W7133361213","https://openalex.org/W4403580118","https://openalex.org/W7009941089","https://openalex.org/W7169543084","https://openalex.org/W7202187488","https://openalex.org/W7153049242","https://openalex.org/W7135336823","https://openalex.org/W7221114059"],"abstract_inverted_index":{"General-purpose":[0],"reward":[1,171,245],"models":[2],"are":[3],"increasingly":[4],"the":[5,12,65,72,143,148],"bottleneck":[6],"for":[7,14,55,204,247],"scaling":[8],"robot":[9,249],"learning,":[10],"yet":[11],"recipe":[13],"learning":[15,103],"value-related":[16],"capabilities":[17],"from":[18,68,82,192,198,213,229],"large-scale":[19],"heterogeneous":[20],"corpora":[21],"remains":[22],"underexplored.":[23],"Existing":[24],"approaches":[25],"tie":[26],"supervision":[27,241],"to":[28,71,86,124,162,194,200,215,231],"task-internal":[29],"anchors":[30,61],"such":[31],"as":[32,219,238],"preferences":[33],"or":[34,97],"normalized":[35],"progress,":[36],"none":[37],"of":[38,138,147,177],"which":[39],"transfer":[40],"cleanly":[41],"across":[42],"embodiments":[43],"and":[44,90,114,126,151,166,197,217,243],"data":[45,205],"sources.":[46],"We":[47],"introduce":[48],"RynnValue,":[49],"an":[50,69,134],"open-source":[51],"value":[52,221],"foundation":[53],"model":[54],"robotic":[56],"manipulation":[57],"that":[58,119],"replaces":[59],"these":[60],"with":[62],"temporal":[63,110,236],"distance,":[64],"directed":[66],"cost-to-go":[67],"observation":[70],"language-specified":[73],"goal.":[74],"Because":[75],"temporal-distance":[76],"labels":[77],"can":[78],"be":[79],"derived":[80],"directly":[81],"timestamps,":[83],"RynnValue":[84,132,173],"scales":[85],"over":[87],"7,000":[88],"hours":[89],"roughly":[91],"3M":[92],"instruction-conditioned":[93],"clips":[94],"without":[95,129],"preference":[96,130],"progress":[98],"annotations.":[99],"To":[100],"make":[101],"temporal-value":[102],"reliable":[104],"at":[105],"scale,":[106],"we":[107],"combine":[108],"random":[109],"sampling,":[111],"temporal-order":[112],"shuffling,":[113],"value-isolation":[115],"attention,":[116],"suppressing":[117],"shortcuts":[118],"would":[120],"leave":[121],"predictions":[122],"insensitive":[123],"failures":[125],"regressions.":[127],"Trained":[128],"labels,":[131],"attains":[133],"average":[135],"Kendall's":[136],"$\u03c4_a$":[137],"0.704":[139],"on":[140],"RBM-EVAL-OOD,":[141],"surpassing":[142],"fully":[144],"preference-supervised":[145],"state":[146],"art":[149],"(0.655)":[150],"more":[152],"than":[153],"doubling":[154],"a":[155,169,175,225,239],"progress-only":[156],"counterpart":[157],"(0.292),":[158],"while":[159],"generalizing":[160],"zero-shot":[161,170],"unseen":[163],"tasks,":[164],"embodiments,":[165],"viewpoints.":[167],"As":[168],"model,":[172],"serves":[174],"range":[176],"downstream":[178],"applications.":[179],"Converted":[180],"into":[181],"dense":[182],"rewards":[183],"via":[184],"potential-based":[185],"shaping,":[186],"it":[187,207,223],"raises":[188],"real-world":[189],"policy":[190],"success":[191,212,228],"52.5%":[193],"72.5%":[195],"online":[196],"63.8%":[199],"82.5%":[201],"offline;":[202],"used":[203],"filtering,":[206],"improves":[208],"multi-task":[209],"behavior":[210],"cloning":[211],"35.0%":[214],"42.5%;":[216],"applied":[218],"inference-time":[220],"guidance,":[222],"lifts":[224],"frozen":[226],"policy's":[227],"67.5%":[230],"80.0%.":[232],"These":[233],"results":[234],"establish":[235],"distance":[237],"scalable":[240],"target":[242],"practical":[244],"interface":[246],"generalist":[248],"policies.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":13}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-12T00:00:00"}