{"id":"https://openalex.org/W7154994000","doi":"https://doi.org/10.48550/arxiv.2604.15871","title":"UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs","display_name":"UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7154994000","doi":"https://doi.org/10.48550/arxiv.2604.15871"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.15871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15871","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.2604.15871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134091487","display_name":"Lifan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Lifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134080641","display_name":"Tianrun Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Tianrun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134012718","display_name":"Yuhang Pei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei, Yuhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134081035","display_name":"Chenyang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chenyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134068604","display_name":"Boxi Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Boxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134070366","display_name":"Deng Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Deng","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.35179999470710754,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.35179999470710754,"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/T11439","display_name":"Video Analysis and Summarization","score":0.22339999675750732,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09160000085830688,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7957000136375427},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7505000233650208},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.583899974822998},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5424000024795532},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4749000072479248},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4503999948501587},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4185999929904938},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.41510000824928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331000208854675},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7957000136375427},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7505000233650208},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123000144958496},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4749000072479248},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4503999948501587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42309999465942383},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3625999987125397},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.15871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15871","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.2604.15871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15871","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":[{"score":0.4531583786010742,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"evaluation":[1,30],"of":[2,82,101],"visual":[3,176],"editing":[4,27,66,177],"models":[5,46,185],"remains":[6],"fragmented":[7],"across":[8],"methods":[9,72],"and":[10,53,64,70,95,108,139,156,170,181],"modalities.":[11],"Existing":[12],"benchmarks":[13],"are":[14,186],"often":[15,36],"tailored":[16],"to":[17,162],"specific":[18],"paradigms,":[19],"making":[20],"fair":[21],"cross-paradigm":[22],"comparisons":[23],"difficult,":[24],"while":[25],"video":[26,65,97],"lacks":[28],"reliable":[29],"benchmarks.":[31],"Furthermore,":[32],"common":[33],"automatic":[34],"metrics":[35],"misalign":[37],"with":[38,99,153],"human":[39,154],"preference,":[40],"yet":[41],"directly":[42],"deploying":[43],"large":[44],"multimodal":[45],"(MLLMs)":[47],"as":[48,106],"evaluators":[49,126,149],"incurs":[50],"prohibitive":[51],"computational":[52],"financial":[54],"costs.":[55],"We":[56],"present":[57],"UniEditBench,":[58],"a":[59,74,79,117,168],"unified":[60],"benchmark":[61,180],"for":[62,173],"image":[63,84],"that":[67,127,146],"supports":[68],"reconstruction-based":[69],"instruction-driven":[71],"under":[73],"shared":[75],"protocol.":[76],"UniEditBench":[77,166],"includes":[78],"structured":[80],"taxonomy":[81],"nine":[83],"operations":[85],"(Add,":[86],"Remove,":[87],"Replace,":[88],"Change,":[89],"Stroke-based,":[90],"Extract,":[91],"Adjust,":[92],"Count,":[93],"Reorder)":[94],"eight":[96],"operations,":[98],"coverage":[100],"challenging":[102],"compositional":[103],"tasks":[104],"such":[105],"counting":[107],"spatial":[109],"reordering.":[110],"To":[111],"enable":[112],"scalable":[113],"evaluation,":[114],"we":[115],"distill":[116],"high-capacity":[118],"MLLM":[119],"judge":[120],"(Qwen3-VL-235B-A22B":[121],"Instruct)":[122],"into":[123],"lightweight":[124],"4B/8B":[125],"provide":[128],"multi-dimensional":[129],"scoring":[130],"over":[131],"structural":[132],"fidelity,":[133],"text":[134],"alignment,":[135],"background":[136],"consistency,":[137],"naturalness,":[138],"temporal-spatial":[140],"consistency":[141],"(for":[142],"videos).":[143],"Experiments":[144],"show":[145],"the":[147,163,182],"distilled":[148],"maintain":[150],"strong":[151],"agreement":[152],"judgments":[155],"substantially":[157],"reduce":[158],"deployment":[159],"cost":[160],"relative":[161],"teacher":[164],"model.":[165],"provides":[167],"practical":[169],"reproducible":[171],"protocol":[172],"benchmarking":[174],"modern":[175],"methods.":[178],"Our":[179],"associated":[183],"reward":[184],"publicly":[187],"available":[188],"at":[189],"https://github.com/wesar1/UniEditBench.":[190]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-21T00:00:00"}