{"id":"https://openalex.org/W7135195707","doi":"https://doi.org/10.48550/arxiv.2603.11846","title":"ZeroSense:How Vision matters in Long Context Compression","display_name":"ZeroSense:How Vision matters in Long Context Compression","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135195707","doi":"https://doi.org/10.48550/arxiv.2603.11846"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.11846","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11846","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":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.2603.11846","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018555925","display_name":"Yonghan Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yonghan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128976593","display_name":"Zehong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zehong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128942848","display_name":"Lijian Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Lijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129017581","display_name":"Jingzhi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jingzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128984326","display_name":"Jingwei Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Jingwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060379760","display_name":"Xingyu Zeng","orcid":"https://orcid.org/0009-0007-8224-4461"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Xingyu","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5220999717712402,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5220999717712402,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.30079999566078186,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.015699999406933784,"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":0.6836000084877014},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6689000129699707},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6177999973297119},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6097000241279602},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5460000038146973},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5390999913215637},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48069998621940613},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4684999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205000162124634},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6836000084877014},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6689000129699707},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5185999870300293},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4510999917984009},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3799000084400177},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3725000023841858},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.11846","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11846","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":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.2603.11846","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11846","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":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":{"Recent":[0],"visual-text":[1],"compression":[2,12],"(VTC)":[3],"methods,":[4],"typified":[5],"by":[6,18,107],"DeepSeek-OCR,":[7],"report":[8],"impressive":[9],"high":[10],"token":[11],"ratios":[13],"for":[14],"long-context":[15],"modeling":[16],"tasks":[17],"leveraging":[19],"text-to-image":[20],"rendering.":[21],"However,":[22],"existing":[23],"evaluation":[24,33,61,98,136],"protocols":[25],"heavily":[26],"rely":[27],"on":[28],"downstream":[29,113,125],"task":[30,126],"performance.":[31],"Such":[32],"metrics":[34],"fail":[35],"to":[36,42,67,81],"accurately":[37],"measure":[38],"text":[39],"preservation":[40],"due":[41],"the":[43,78,97,108,131],"strong":[44],"inherent":[45],"linguistic":[46],"priors":[47],"of":[48,86,103,112,133],"Multimodal":[49],"Large":[50],"Language":[51],"Models":[52],"(MLLMs).":[53],"In":[54],"this":[55,73],"work,":[56],"we":[57,75],"introduce":[58,77],"a":[59],"new":[60],"framework":[62],"that":[63,96,121],"decouples":[64],"MLLMs'":[65],"capabilities":[66,111],"faithfully":[68],"assess":[69],"VTC":[70,104,122],"quality.":[71],"Within":[72],"framework,":[74],"further":[76],"ZeroSense":[79],"Benchmark":[80],"ensure":[82],"low":[83],"semantic":[84,109],"correlation":[85],"testing":[87],"samples.":[88],"By":[89],"eliminating":[90],"contextual":[91],"dependencies,":[92],"our":[93,134],"benchmark":[94],"guarantees":[95],"results":[99],"are":[100],"purely":[101],"reflective":[102],"quality,":[105],"unaffected":[106],"inference":[110],"models.":[114],"Extensive":[115],"experiments":[116],"across":[117],"multiple":[118],"datasets":[119],"demonstrate":[120],"quality":[123],"and":[124],"accuracy":[127],"diverge":[128],"significantly,":[129],"highlighting":[130],"necessity":[132],"decoupled":[135],"framework.":[137]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-14T00:00:00"}