{"id":"https://openalex.org/W7154062543","doi":"https://doi.org/10.48550/arxiv.2604.09450","title":"ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion","display_name":"ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion","publication_year":2026,"publication_date":"2026-04-10","ids":{"openalex":"https://openalex.org/W7154062543","doi":"https://doi.org/10.48550/arxiv.2604.09450"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.09450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09450","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":null,"license_id":null,"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.2604.09450","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133546716","display_name":"Lifeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Lifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133515066","display_name":"Tianqi You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You, Tianqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133508643","display_name":"Hao Liu","orcid":"https://orcid.org/0009-0006-6022-629X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133549397","display_name":"Zhimin Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Zhimin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006378664","display_name":"Jile Jiao","orcid":"https://orcid.org/0000-0003-2644-717X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Jile","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133503729","display_name":"Xiao Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059715879","display_name":"Zhicai Ou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ou, Zhicai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133521077","display_name":"Tao Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133493182","display_name":"Xiaofeng Mou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mou, Xiaofeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668699","display_name":"Xiaojie Jin","orcid":"https://orcid.org/0000-0002-7850-1353"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Xiaojie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133512813","display_name":"Yi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yi","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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.3797000050544739,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.3797000050544739,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.2770000100135803,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0471000000834465,"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/autoregressive-model","display_name":"Autoregressive model","score":0.6164000034332275},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6144000291824341},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6028000116348267},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4447999894618988},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.41429999470710754},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.3953000009059906},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.3772999942302704},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178000211715698},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6164000034332275},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6144000291824341},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46299999952316284},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41110000014305115},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C149550507","wikidata":"https://www.wikidata.org/wiki/Q899360","display_name":"Diffusion MRI","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.09450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09450","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.09450","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09450","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":null,"license_id":null,"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":{"Chest":[0],"X-ray":[1,84],"report":[2,85],"generation":[3],"(CXR-RG)":[4],"has":[5],"the":[6,63,102],"potential":[7],"to":[8,25,48,62,113,158],"substantially":[9],"alleviate":[10],"radiologists'":[11],"workload.":[12],"However,":[13],"conventional":[14],"autoregressive":[15,144],"vision--language":[16],"models":[17,30],"(VLMs)":[18],"suffer":[19],"from":[20,109],"high":[21],"inference":[22,91,160],"latency":[23],"due":[24,61],"sequential":[26],"token":[27,116],"decoding.":[28],"Diffusion-based":[29],"offer":[31],"a":[32,49,93,122],"promising":[33],"alternative":[34],"through":[35],"parallel":[36],"generation,":[37],"but":[38,56],"they":[39],"still":[40],"require":[41],"multiple":[42],"denoising":[43,47],"iterations.":[44],"Compressing":[45],"multi-step":[46],"single":[50],"step":[51],"could":[52],"further":[53,129],"reduce":[54],"latency,":[55],"often":[57],"degrades":[58],"textual":[59],"coherence":[60],"mean-field":[64,103],"bias":[65],"introduced":[66],"by":[67,105,150],"token-factorized":[68],"denoisers.":[69],"To":[70],"address":[71],"this":[72],"challenge,":[73],"we":[74,120],"propose":[75],"\\textbf{ECHO},":[76],"an":[77],"efficient":[78],"diffusion-based":[79],"VLM":[80],"(dVLM)":[81],"for":[82],"chest":[83],"generation.":[86],"ECHO":[87,141],"enables":[88],"stable":[89],"one-step-per-block":[90],"via":[92],"novel":[94],"Direct":[95],"Conditional":[96],"Distillation":[97],"(DCD)":[98],"framework,":[99],"which":[100],"mitigates":[101],"limitation":[104],"constructing":[106],"unfactorized":[107],"supervision":[108],"on-policy":[110],"diffusion":[111],"trajectories":[112],"encode":[114],"joint":[115],"dependencies.":[117],"In":[118],"addition,":[119],"introduce":[121],"Response-Asymmetric":[123],"Diffusion":[124],"(RAD)":[125],"training":[126,131],"strategy":[127],"that":[128,140],"improves":[130],"efficiency":[132],"while":[133,155],"maintaining":[134],"model":[135],"effectiveness.":[136],"Extensive":[137],"experiments":[138],"demonstrate":[139],"surpasses":[142],"state-of-the-art":[143],"methods,":[145],"improving":[146],"RaTE":[147],"and":[148,152],"SemScore":[149],"\\textbf{64.33\\%}":[151],"\\textbf{60.58\\%}":[153],"respectively,":[154],"achieving":[156],"up":[157],"\\textbf{$8\\times$}":[159],"speedup":[161],"with":[162],"negligible":[163],"degradation":[164],"in":[165],"clinical":[166],"accuracy.":[167]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-14T00:00:00"}