{"id":"https://openalex.org/W4417010743","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1782","title":"Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules","display_name":"Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417010743","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1782"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1782","pdf_url":"https://aclanthology.org/2026.findings-acl.1782.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1782.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103627355","display_name":"Amr E. Mohamed","orcid":"https://orcid.org/0000-0002-2987-5391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amr Mohamed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354763","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0003-1011-3001"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085652160","display_name":"Michalis Vazirgiannis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michalis Vazirgiannis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038162261","display_name":"Guokan Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guokan Shang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0308192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35793","last_page":"35807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6462000012397766,"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":0.6462000012397766,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.06040000170469284,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.033799998462200165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6297000050544739},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5608000159263611},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5508000254631042},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47859999537467957},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4320000112056732},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4309000074863434},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41119998693466187},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4050999879837036},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3723999857902527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817000150680542},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6297000050544739},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5608000159263611},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5508000254631042},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3407000005245209},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3310000002384186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3296000063419342},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1782","pdf_url":"https://aclanthology.org/2026.findings-acl.1782.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.02892","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.02892","pdf_url":"https://arxiv.org/pdf/2512.02892","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.02892","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.02892","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,"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:10.18653/v1/2026.findings-acl.1782","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1782","pdf_url":"https://aclanthology.org/2026.findings-acl.1782.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417010743.pdf","grobid_xml":"https://content.openalex.org/works/W4417010743.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"large":[1],"language":[2],"models":[3],"(dLLMs)":[4],"offer":[5],"a":[6,25,35,47,95,141,148],"promising":[7],"alternative":[8],"to":[9,89,115],"autoregressive":[10],"models,":[11,64,77],"but":[12],"their":[13],"practical":[14],"utility":[15],"is":[16],"severely":[17],"hampered":[18],"by":[19],"slow,":[20],"iterative":[21],"sampling.We":[22],"present":[23],"SchED,":[24],"training-free,":[26],"model-agnostic":[27],"early-exit":[28,105],"algorithm":[29],"that":[30,126],"terminates":[31],"diffusion":[32,43],"decoding":[33],"using":[34],"progress-aware":[36],"confidence":[37,138],"threshold.We":[38],"evaluate":[39],"SchED":[40,78,100,146],"across":[41],"multiple":[42],"model":[44],"families":[45],"and":[46,57],"diverse":[48],"set":[49],"of":[50,120,133],"benchmarks":[51],"spanning":[52],"multiple-choice,":[53],"math,":[54],"long-form":[55,109],"QA,":[56],"translation.SchED":[58],"delivers":[59],"substantial":[60],"acceleration:":[61],"on":[62,74,108],"instruction-tuned":[63],"it":[65],"achieves":[66],"approximately":[67],"4\u00d7":[68],"speedups":[69],"while":[70],"retaining":[71],"baseline":[72],"performance":[73,85],"average.On":[75],"base":[76],"yields":[79],"consistent":[80],"speedup":[81],"gains":[82],"with":[83,87],"99.1-100%":[84],"retention,":[86],"up":[88,130],"2.34\u00d7":[90],"under":[91],"more":[92],"aggressive":[93],"settings.Under":[94],"conservative":[96],"quality-penalized":[97],"speed":[98],"metric,":[99],"consistently":[101],"outperforms":[102],"prior":[103],"confidence-based":[104],"methods,":[106],"including":[107],"generation":[110],"where":[111],"existing":[112],"approaches":[113],"tend":[114],"break":[116],"down.An":[117],"entropy":[118],"analysis":[119],"the":[121,131],"model's":[122],"token":[123],"predictions":[124],"reveals":[125],"instruction":[127],"tuning":[128],"speeds":[129],"decay":[132],"predictive":[134],"entropy.By":[135],"leveraging":[136],"inherent":[137],"stabilization":[139],"as":[140],"signal":[142],"for":[143,151],"computational":[144],"efficiency,":[145],"provides":[147],"robust":[149],"framework":[150],"efficient":[152],"dLLM":[153],"inference.":[154]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-12-04T00:00:00"}