{"id":"https://openalex.org/W7137823895","doi":"https://doi.org/10.48550/arxiv.2603.15340","title":"DOS: Dependency-Oriented Sampler for Masked Diffusion Language Models","display_name":"DOS: Dependency-Oriented Sampler for Masked Diffusion Language Models","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7137823895","doi":"https://doi.org/10.48550/arxiv.2603.15340"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.15340","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15340","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.2603.15340","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129723060","display_name":"Xueyu Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Xueyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129645870","display_name":"Yangrong Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yangrong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129651197","display_name":"Jian Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jian","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/T10028","display_name":"Topic Modeling","score":0.3765999972820282,"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/T10028","display_name":"Topic Modeling","score":0.3765999972820282,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11400000005960464,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.07360000163316727,"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/decoding-methods","display_name":"Decoding methods","score":0.73580002784729},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6563000082969666},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6111999750137329},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5248000025749207},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43959999084472656},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3887999951839447},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.38190001249313354},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.376800000667572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965999841690063},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.73580002784729},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6563000082969666},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5248000025749207},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4569999873638153},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43959999084472656},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.38190001249313354},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.376800000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3675999939441681},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.365200012922287},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.15340","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15340","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.2603.15340","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15340","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Masked":[0],"diffusion":[1],"language":[2,13],"models":[3],"(MDLMs)":[4],"have":[5],"recently":[6],"emerged":[7],"as":[8],"a":[9,54],"new":[10],"paradigm":[11],"in":[12],"modeling,":[14],"offering":[15],"flexible":[16],"generation":[17,101,120,124],"dynamics":[18],"and":[19,42,102],"enabling":[20],"efficient":[21],"parallel":[22,114],"decoding.":[23],"However,":[24],"existing":[25,113],"decoding":[26,56],"strategies":[27],"for":[28],"pre-trained":[29],"MDLMs":[30],"predominantly":[31],"rely":[32],"on":[33,98],"token-level":[34],"uncertainty":[35],"criteria,":[36],"while":[37],"largely":[38],"overlooking":[39],"sequence-level":[40],"information":[41,81],"inter-token":[43,60,78],"dependencies.":[44],"To":[45],"address":[46],"this":[47],"limitation,":[48],"we":[49],"propose":[50],"Dependency-Oriented":[51],"Sampler":[52],"(DOS),":[53],"training-free":[55],"strategy":[57],"that":[58,92],"leverages":[59],"dependencies":[61],"to":[62,76,118],"inform":[63],"token":[64],"updates":[65],"during":[66],"generation.":[67],"Specifically,":[68],"DOS":[69,93,107],"exploits":[70],"attention":[71],"matrices":[72],"from":[73,82],"transformer":[74],"blocks":[75],"approximate":[77],"dependencies,":[79],"emphasizing":[80],"unmasked":[83],"tokens":[84],"when":[85],"updating":[86],"masked":[87],"positions.":[88],"Empirical":[89],"results":[90],"demonstrate":[91],"consistently":[94],"achieves":[95],"superior":[96],"performance":[97],"both":[99],"code":[100],"mathematical":[103],"reasoning":[104],"tasks.":[105],"Moreover,":[106],"can":[108],"be":[109],"seamlessly":[110],"integrated":[111],"with":[112],"sampling":[115],"methods,":[116],"leading":[117],"improved":[119],"efficiency":[121],"without":[122],"sacrificing":[123],"quality.":[125]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-18T00:00:00"}