{"id":"https://openalex.org/W7108954609","doi":"https://doi.org/10.18653/2026.emnlp-main.909","title":"Decoding Diffusion Language Models with Foreseeing Movement","display_name":"Decoding Diffusion Language Models with Foreseeing Movement","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7108954609","doi":"https://doi.org/10.18653/2026.emnlp-main.909"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.909","doi":"https://doi.org/10.18653/2026.emnlp-main.909","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.909","pdf_url":"https://aclanthology.org/2026.emnlp-main.909.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.909.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yichuan Mo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichuan Mo","raw_affiliation_strings":["State Key Lab of General Artificial Intelligence , School of Intelligence Science and Technology , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of General Artificial Intelligence , School of Intelligence Science and Technology , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Quan Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Chen","raw_affiliation_strings":["School of Mathematical Sciences , Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences , Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingjie Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mingjie Li","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security , Germany ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security , Germany ,","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zeming Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeming Wei","raw_affiliation_strings":["School of Mathematical Sciences , Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences , Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yisen Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisen Wang","raw_affiliation_strings":["State Key Lab of General Artificial Intelligence , School of Intelligence Science and Technology , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of General Artificial Intelligence , School of Intelligence Science and Technology , Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.02881069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20943","last_page":"20958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4961000084877014,"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":0.4961000084877014,"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":0.47850000858306885,"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":0.00419999985024333,"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/decoding-order","display_name":"decoding order","score":0.6110000014305115},{"id":"https://openalex.org/keywords/token-selection","display_name":"token selection","score":0.5910000205039978},{"id":"https://openalex.org/keywords/controllable-generation","display_name":"controllable generation","score":0.8960000276565552},{"id":"https://openalex.org/keywords/performance-efficiency-trade-off","display_name":"performance-efficiency trade-off","score":0.8420000076293945}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8636999726295471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731000185012817},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5813999772071838},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5799000263214111},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5482000112533569},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C193969084","wikidata":"https://www.wikidata.org/wiki/Q7452500","display_name":"Sequential decoding","level":4,"score":0.43160000443458557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41370001435279846},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3531999886035919},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.909","doi":"https://doi.org/10.18653/2026.emnlp-main.909","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.909","pdf_url":"https://aclanthology.org/2026.emnlp-main.909.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.04135","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.04135","pdf_url":"https://arxiv.org/pdf/2512.04135","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.04135","doi":"https://doi.org/10.48550/arxiv.2512.04135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.04135","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.909","doi":"https://doi.org/10.18653/2026.emnlp-main.909","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.909","pdf_url":"https://aclanthology.org/2026.emnlp-main.909.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7108954609.pdf","grobid_xml":"https://content.openalex.org/works/W7108954609.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416366283","https://openalex.org/W7118527898","https://openalex.org/W4415318060","https://openalex.org/W7126110285","https://openalex.org/W7213433715","https://openalex.org/W7165026022","https://openalex.org/W7126001854","https://openalex.org/W4414805728","https://openalex.org/W7078172510","https://openalex.org/W7155214498"],"abstract_inverted_index":{"Diffusion":[0],"Language":[1],"Models":[2],"(DLMs)":[3],"benefit":[4],"from":[5],"a":[6,23,59,75,99,144],"flexible":[7],"decoding":[8,33,95,150],"mechanism":[9],"that":[10,62],"enables":[11],"parallelized":[12],"inference":[13,26],"and":[14,66,116,123,131],"controllable":[15],"generations":[16],"over":[17],"autoregressive":[18],"models.Yet":[19],"such":[20],"flexibility":[21],"introduces":[22],"critical":[24,110],"challenge:":[25],"performance":[27],"becomes":[28],"highly":[29],"sensitive":[30],"to":[31,69,78,109],"the":[32,54,71,87,93,114,127,133],"order":[34],"of":[35,89,129],"tokens.Existing":[36],"heuristic":[37],"methods,":[38],"however,":[39],"focus":[40],"mainly":[41],"on":[42],"local":[43,65],"effects":[44],"while":[45],"overlooking":[46],"long-term":[47],"impacts.To":[48],"address":[49],"this":[50],"limitation,":[51],"we":[52,97],"propose":[53],"Foreseeing":[55],"Decoding":[56],"Method":[57],"(FDM),":[58],"novel":[60],"approach":[61],"integrates":[63],"both":[64],"global":[67],"considerations":[68],"unlock":[70],"full":[72,94],"potential,":[73],"employing":[74],"search-based":[76],"strategy":[77],"enable":[79],"effective":[80],"optimization":[81],"in":[82,92],"discrete":[83],"spaces.Furthermore,":[84],"by":[85,138],"analyzing":[86],"consistency":[88],"chosen":[90],"tokens":[91],"process,":[96],"develop":[98],"variant,":[100],"FDM":[101,130],"with":[102],"Acceleration":[103],"(FDM-A),":[104],"which":[105],"restricts":[106],"deep":[107],"exploration":[108,115],"steps":[111],"identified":[112],"as":[113],"balance":[117],"circumstances.Extensive":[118],"experiments":[119],"across":[120],"diverse":[121],"benchmarks":[122],"model":[124],"architectures":[125],"validate":[126],"scalability":[128],"demonstrate":[132],"superior":[134],"efficiencyperformance":[135],"trade-off":[136],"achieved":[137],"FDM-A.Our":[139],"work":[140],"might":[141],"potentially":[142],"provide":[143],"principled":[145],"step":[146],"toward":[147],"more":[148],"powerful":[149],"methods":[151],"for":[152],"DLMs.Our":[153],"code":[154],"is":[155],"available":[156],"at":[157],"https://github.com/PKU-ML/FDM.":[158]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2025-12-06T00:00:00"}