{"id":"https://openalex.org/W7163578220","doi":"https://doi.org/10.48550/arxiv.2606.04945","title":"STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models","display_name":"STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163578220","doi":"https://doi.org/10.48550/arxiv.2606.04945"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.04945","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04945","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.2606.04945","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137887900","display_name":"Xin Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049401169","display_name":"Aqiang Wang","orcid":"https://orcid.org/0009-0007-5317-4687"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Aqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137894806","display_name":"Zhenglin Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Zhenglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137881657","display_name":"Xingrui Yuand Ivor Tsang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xingrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Tsang, Ivor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsang, Ivor","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/T10036","display_name":"Advanced Neural Network Applications","score":0.608299970626831,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.608299970626831,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11420000344514847,"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":0.03420000150799751,"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/quantization","display_name":"Quantization (signal processing)","score":0.6912000179290771},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.5461999773979187},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.43650001287460327},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.42820000648498535},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4131999909877777},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.40119999647140503},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.39649999141693115}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6912000179290771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6272000074386597},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.5461999773979187},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4984000027179718},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41690000891685486},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3653999865055084},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3321000039577484},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26460000872612},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.04945","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04945","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.2606.04945","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04945","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":{"Diffusion":[0],"large":[1,27],"language":[2],"models":[3],"(DLLMs)":[4],"have":[5],"recently":[6],"emerged":[7],"as":[8],"a":[9,94,119,138],"promising":[10],"alternative":[11],"to":[12,107,113,131,162],"autoregressive":[13],"LLMs":[14],"by":[15],"generating":[16],"text":[17],"through":[18],"iterative":[19,31,85],"masked":[20,109],"denoising":[21,32,75],"with":[22,118],"bidirectional":[23],"context.":[24],"However,":[25],"their":[26],"model":[28],"sizes":[29],"and":[30,37,61,66,110,165],"process":[33],"introduce":[34],"substantial":[35],"memory":[36,167],"computational":[38],"overhead,":[39],"motivating":[40],"post-training":[41],"quantization":[42,78,154],"for":[43,54,99],"efficient":[44],"deployment.":[45,171],"In":[46],"this":[47],"paper,":[48],"we":[49,91],"identify":[50],"two":[51],"key":[52],"challenges":[53],"low-bit":[55,152],"DLLM":[56],"quantization:":[57],"state-dependent":[58],"activation":[59,71,115],"disparity":[60],"temporal":[62],"error":[63],"accumulation.":[64],"Masked":[65],"unmasked":[67,111],"tokens":[68,112],"exhibit":[69],"different":[70,114],"distributions":[72],"within":[73],"each":[74],"step,":[76],"while":[77,159],"errors":[79],"can":[80],"accumulate":[81],"across":[82],"steps":[83],"during":[84],"decoding.":[86],"To":[87],"address":[88],"these":[89],"challenges,":[90],"propose":[92],"STaR-Quant,":[93],"state-time":[95],"consistent":[96],"PTQ":[97,157],"framework":[98],"DLLMs.":[100],"STaR-Quant":[101,149],"introduces":[102,126],"State-Guided":[103],"Activation":[104],"Transformation":[105],"(SGAT)":[106],"assign":[108],"transformation":[116],"spaces":[117],"unified":[120],"static":[121],"weight-side":[122],"transformation.":[123],"It":[124],"further":[125],"Temporal":[127],"Attention":[128],"Compensation":[129],"(TAC)":[130],"correct":[132],"the":[133],"quantized":[134],"attention":[135],"representation":[136],"via":[137],"lightweight":[139],"block-diagonal":[140],"affine":[141],"mapping.":[142],"Experiments":[143],"on":[144],"representative":[145],"DLLMs":[146],"demonstrate":[147],"that":[148],"consistently":[150],"improves":[151],"weight-activation":[153],"over":[155,169],"strong":[156],"baselines,":[158],"delivering":[160],"up":[161],"1.69x":[163],"speedup":[164],"3.14x":[166],"saving":[168],"FP16":[170]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-05T00:00:00"}