{"id":"https://openalex.org/W7150770562","doi":"https://doi.org/10.48550/arxiv.2604.03231","title":"CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning","display_name":"CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning","publication_year":2026,"publication_date":"2026-04-03","ids":{"openalex":"https://openalex.org/W7150770562","doi":"https://doi.org/10.48550/arxiv.2604.03231"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.03231","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03231","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.2604.03231","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107585272","display_name":"Ankan Deria","orcid":"https://orcid.org/0009-0003-1589-0296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deria, Ankan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125399626","display_name":"Komal Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Komal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101302819","display_name":"Xilin He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Xilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121288446","display_name":"Imran Razzak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Razzak, Imran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009362997","display_name":"Hisham Cholakkal","orcid":"https://orcid.org/0000-0002-8230-9065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cholakkal, Hisham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133019055","display_name":"Fahad Shahbaz Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Fahad Shahbaz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133030698","display_name":"Salman Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Salman","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":0.541100025177002,"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":0.541100025177002,"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":0.12229999899864197,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.08209999650716782,"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/encoder","display_name":"Encoder","score":0.667900025844574},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6444000005722046},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5062000155448914},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.475600004196167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4099999964237213},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3986999988555908},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.3903000056743622},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.38920000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498999834060669},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.667900025844574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6552000045776367},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6444000005722046},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41040000319480896},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3564999997615814},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.29989999532699585},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C2779726219","wikidata":"https://www.wikidata.org/wiki/Q7685884","display_name":"Target acquisition","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.03231","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03231","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.2604.03231","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03231","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"vision-language":[1,63,139],"models":[2],"(VLMs)":[3],"typically":[4],"rely":[5],"on":[6,42,157,163,171,189],"a":[7,71,77,83,125,181],"single":[8],"vision":[9,80],"encoder":[10,81],"trained":[11,79],"with":[12,82,97,128],"contrastive":[13,21,202],"image-text":[14],"objectives,":[15],"such":[16],"as":[17],"CLIP-style":[18],"pretraining.":[19],"While":[20],"encoders":[22,32],"are":[23],"effective":[24],"for":[25,62,173],"cross-modal":[26],"alignment":[27],"and":[28,38,44,103,112,161,195,203],"retrieval,":[29],"self-supervised":[30,84,204],"visual":[31,60,116,158],"often":[33],"capture":[34],"richer":[35],"dense":[36],"semantics":[37],"exhibit":[39],"stronger":[40],"robustness":[41],"recognition":[43],"understanding":[45,159],"tasks.":[46,165],"In":[47,148],"this":[48],"work,":[49],"we":[50,150,185],"investigate":[51],"how":[52,200],"to":[53,100,107,131,198],"scale":[54],"the":[55,178],"fusion":[56,73,91,196],"of":[57,155],"these":[58],"complementary":[59,201],"representations":[61],"modeling.":[64],"We":[65],"propose":[66],"CoME-VL:":[67],"Complementary":[68],"Multi-Encoder":[69],"Vision-Language,":[70],"modular":[72],"framework":[74],"that":[75,142],"integrates":[76],"contrastively":[78],"DINO":[85],"encoder.":[86],"Our":[87,166],"approach":[88],"performs":[89],"representation-level":[90],"by":[92,180],"(i)":[93],"entropy-guided":[94],"multi-layer":[95],"aggregation":[96],"orthogonality-constrained":[98],"projections":[99],"reduce":[101],"redundancy,":[102],"(ii)":[104],"RoPE-enhanced":[105],"cross-attention":[106],"align":[108],"heterogeneous":[109],"token":[110],"grids":[111],"produce":[113],"compact":[114],"fused":[115,119],"tokens.":[117],"The":[118],"tokens":[120],"can":[121],"be":[122],"injected":[123],"into":[124],"decoder-only":[126],"LLM":[127],"minimal":[129],"changes":[130],"standard":[132],"VLM":[133,207],"pipelines.":[134],"Extensive":[135],"experiments":[136],"across":[137],"diverse":[138],"benchmarks":[140],"demonstrate":[141],"CoME-VL":[143],"consistently":[144],"outperforms":[145],"single-encoder":[146],"baselines.":[147],"particular,":[149],"observe":[151],"an":[152],"average":[153],"improvement":[154],"4.9%":[156],"tasks":[160],"5.4%":[162],"grounding":[164],"method":[167],"achieves":[168],"state-of-the-art":[169],"performance":[170],"RefCOCO":[172],"detection":[174],"while":[175],"improving":[176],"over":[177],"baseline":[179],"large":[182],"margin.":[183],"Finally,":[184],"conduct":[186],"ablation":[187],"studies":[188],"layer":[190],"merging,":[191],"non-redundant":[192],"feature":[193],"mixing,":[194],"capacity":[197],"evaluate":[199],"signals":[205],"affect":[206],"performance.":[208]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-07T00:00:00"}