{"id":"https://openalex.org/W7165654575","doi":"https://doi.org/10.48550/arxiv.2606.23623","title":"dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models","display_name":"dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165654575","doi":"https://doi.org/10.48550/arxiv.2606.23623"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.23623","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.23623","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.23623","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139174930","display_name":"Yuhao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yuhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120711668","display_name":"Yitian Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yitian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110830067","display_name":"Weijie Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Weijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139197887","display_name":"Mishuo Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Mishuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139200413","display_name":"Wenjie Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Wenjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139188505","display_name":"Haotian Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Haotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139203075","display_name":"Zhongshan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhongshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121791671","display_name":"Yinan Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Yinan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015286750","display_name":"Lei Xu","orcid":"https://orcid.org/0009-0003-1055-9318"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139136216","display_name":"Xinping Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Xinping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139147758","display_name":"Ru Ying","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying, Ru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017367101","display_name":"Ran Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Ran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139169925","display_name":"Wei Sui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sui, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030018760","display_name":"Xiaomin Yang","orcid":"https://orcid.org/0000-0002-5593-5108"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xiaokang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139179379","display_name":"Wenbo Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Wenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139205156","display_name":"Yao Mu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mu, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5911999940872192,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5911999940872192,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.22849999368190765,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.050999999046325684,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6230000257492065},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.553600013256073},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.3626999855041504},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.35519999265670776},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.35260000824928284},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.349700003862381},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3400000035762787},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.3393999934196472},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.3264999985694885}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6230000257492065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6164000034332275},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.553600013256073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48899999260902405},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3695000112056732},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2892000079154968},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.23623","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.23623","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.23623","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.23623","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":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6871457695960999}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2],"have":[3,46],"established":[4],"a":[5,49,58,151,163,172,187,218,236],"powerful":[6],"paradigm":[7],"for":[8,92,103,192],"generalist":[9],"robotic":[10],"manipulation":[11],"by":[12,115,145,234],"grounding":[13],"control":[14],"into":[15,57],"the":[16,86,107,111,127,131,136,140,147,240],"semantic":[17],"reasoning":[18],"of":[19,88,110,139,165,221],"VLMs.":[20],"Prevailing":[21],"architectures":[22],"typically":[23],"model":[24],"actions":[25],"continuously":[26],"via":[27,63],"diffusion":[28],"or":[29,32,38],"flow":[30],"processes,":[31],"discretely":[33],"through":[34],"either":[35],"autoregressive":[36],"generation":[37,142],"parallel":[39],"decoding.":[40],"Recently,":[41],"Discrete":[42],"Diffusion":[43],"VLAs":[44],"(dVLAs)":[45],"emerged":[47],"as":[48,150,162],"distinct":[50],"alternative,":[51],"unifying":[52],"vision,":[53],"language,":[54],"and":[55,208],"action":[56,113,133],"single":[59],"discrete":[60],"token":[61],"space":[62],"masked":[64],"generative":[65],"modeling.":[66],"While":[67],"combining":[68],"iterative":[69],"refinement":[70,95],"with":[71,245],"unified":[72,173,188],"representations,":[73],"its":[74],"training":[75],"has":[76],"thus":[77],"far":[78],"been":[79],"restricted":[80],"to":[81,135,199,203],"Supervised":[82],"Fine-Tuning":[83],"(SFT),":[84],"leaving":[85],"potential":[87],"Reinforcement":[89],"Learning":[90],"(RL)":[91],"further":[93],"policy":[94],"largely":[96],"unexplored.":[97],"A":[98],"fundamental":[99],"challenge":[100],"in":[101],"RL":[102],"dVLAs":[104,116],"is":[105],"that":[106,175,214],"marginal":[108,132],"probability":[109,134,138,161],"final":[112],"generated":[114],"remains":[117],"intractable.":[118],"To":[119],"solve":[120],"this":[121,159,182],"problem,":[122],"we":[123,156,185],"propose":[124],"\\textbf{dVLA-RL},":[125],"shifting":[126],"learning":[128],"objective":[129,170],"from":[130],"joint":[137],"sampled":[141],"path.":[143],"Specifically,":[144],"modeling":[146],"denoising":[148,179,197],"process":[149],"Markov":[152],"Decision":[153],"Process":[154],"(MDP),":[155],"mathematically":[157],"formulate":[158],"path":[160],"product":[164],"step-wise":[166],"transitions.":[167],"This":[168],"trajectory-level":[169],"provides":[171],"formulation":[174],"natively":[176],"accommodates":[177],"variable":[178],"steps.":[180],"Leveraging":[181],"intrinsic":[183],"fexibility,":[184],"introduce":[186],"step":[189],"scheduling":[190],"approach":[191,216],"complex":[193],"multi-task":[194],"learning,":[195],"tailoring":[196],"steps":[198],"specific":[200],"task":[201],"complexities":[202],"maximize":[204],"both":[205],"success":[206,219],"rates":[207],"computational":[209],"effciency.":[210],"Extensive":[211],"evaluations":[212],"demonstrate":[213],"our":[215],"achieves":[217],"rate":[220],"\\textbf{99.7\\%}":[222],"on":[223,231],"LIBERO.":[224],"Furthermore,":[225],"it":[226],"establishes":[227],"strong":[228,246],"VLA-based":[229],"results":[230],"RoboTwin":[232],"2.0":[233],"delivering":[235],"\\textbf{30.6\\%}":[237],"improvement":[238],"over":[239],"SFT":[241],"baseline,":[242],"remaining":[243],"competitive":[244],"World-Action":[247],"Model":[248],"baselines.":[249]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}