{"id":"https://openalex.org/W7214950557","doi":"https://doi.org/10.48550/arxiv.2609.37685","title":"PAIQ: Patch-Aligned Semantic Injection via Residual Rotation","display_name":"PAIQ: Patch-Aligned Semantic Injection via Residual Rotation","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214950557","doi":"https://doi.org/10.48550/arxiv.2609.37685"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37685","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37685","pdf_url":"https://arxiv.org/pdf/2609.37685","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100585426","display_name":"Pinze Ren","orcid":"https://orcid.org/0009-0006-3090-7596","observed_orcids":["https://orcid.org/0009-0006-3090-7596"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren, Pinze","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153661079","display_name":"Yuwei Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Yuwei","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153650942","display_name":"Hao Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Hao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153615706","display_name":"Linghao Meng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Linghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153653169","display_name":"Chang Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Chang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153625574","display_name":"Qiankun Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Li, Qiankun","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":1.0,"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":1.0,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/residual-rotation","display_name":"residual rotation","score":0.7649999856948853},{"id":"https://openalex.org/keywords/orthogonal-transformations","display_name":"orthogonal transformations","score":0.8050000071525574},{"id":"https://openalex.org/keywords/dinov3","display_name":"DINOv3","score":0.8389999866485596},{"id":"https://openalex.org/keywords/siglip","display_name":"SigLIP","score":0.972000002861023},{"id":"https://openalex.org/keywords/image-description-generation","display_name":"image description generation","score":0.6230000257492065},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.9980000257492065},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.9629999995231628}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7153000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.66839998960495},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6061000227928162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501000285148621},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.47279998660087585},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45669999718666077},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4023999869823456},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32030001282691956},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.30149999260902405},{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C152279782","wikidata":"https://www.wikidata.org/wiki/Q13583542","display_name":"Shearing (physics)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2818000018596649},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C167729594","wikidata":"https://www.wikidata.org/wiki/Q17736","display_name":"Axiom","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37685","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37685","pdf_url":"https://arxiv.org/pdf/2609.37685","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.37685","doi":"https://doi.org/10.48550/arxiv.2609.37685","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37685","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37685","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37685","pdf_url":"https://arxiv.org/pdf/2609.37685","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214950557.pdf","grobid_xml":"https://content.openalex.org/works/W7214950557.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2886641317","https://openalex.org/W2934842096","https://openalex.org/W4366208220","https://openalex.org/W4385473806","https://openalex.org/W4387687151","https://openalex.org/W4390873312","https://openalex.org/W4402706175","https://openalex.org/W4403842477","https://openalex.org/W4407815020","https://openalex.org/W4413146712","https://openalex.org/W4415796658","https://openalex.org/W7081571182","https://openalex.org/W7134918669","https://openalex.org/W7150770562","https://openalex.org/W7166815624"],"related_works":["https://openalex.org/W4402715976","https://openalex.org/W4415945620","https://openalex.org/W7204257342","https://openalex.org/W7168169381","https://openalex.org/W4416075251","https://openalex.org/W7222286590","https://openalex.org/W7203783720","https://openalex.org/W3184735396","https://openalex.org/W4281676132","https://openalex.org/W7160898446"],"abstract_inverted_index":{"Language-aligned":[0],"and":[1,11,63,83,100,120,128,134,151,162,169],"self-supervised":[2],"visual":[3,126,138,163],"encoders":[4,127],"offer":[5],"complementary":[6,56],"strengths":[7],"in":[8,148,153],"semantic":[9,33,98],"abstraction":[10],"spatial":[12,52],"detail.":[13],"Harnessing":[14],"this":[15,173],"complementarity":[16],"requires":[17],"enriching":[18],"local":[19],"features":[20,49,58],"while":[21,79],"retaining":[22],"distinctions":[23],"between":[24],"semantically":[25],"related":[26],"patches.":[27],"We":[28],"introduce":[29],"PAIQ,":[30],"a":[31,69,105],"patch-aligned":[32],"injection":[34],"framework":[35],"that":[36,102],"combines":[37],"content-based":[38],"cross-encoder":[39],"matching":[40],"with":[41],"orthogonally":[42],"constrained":[43],"residual":[44,81],"updates.":[45],"Using":[46],"DINOv3":[47],"patch":[48,94],"as":[50],"the":[51,65,113,118,129,167,177],"base,":[53],"PAIQ":[54,144],"aggregates":[55,99],"SigLIP":[57],"through":[59,68],"joint":[60],"source":[61],"allocation":[62],"injects":[64],"aggregate--base":[66],"differences":[67],"shared":[70],"orthogonal":[71],"transformation":[72],"Q.":[73],"This":[74],"rotation":[75,103],"adapts":[76],"update":[77],"directions":[78],"preserving":[80],"norms":[82],"pairwise":[84],"angles.":[85],"For":[86],"fixed":[87],"projected":[88],"features,":[89],"we":[90],"derive":[91],"conditions":[92],"for":[93],"separability":[95],"under":[96],"similar":[97],"show":[101],"adds":[104],"nonnegative":[106],"separation":[107],"term":[108],"over":[109,156],"direct":[110],"interpolation":[111],"when":[112],"aggregate":[114],"is":[115],"shared.":[116],"Only":[117],"projection":[119],"fusion":[121,135,180],"parameters":[122],"are":[123],"trained;":[124],"both":[125],"language":[130,142],"model":[131],"remain":[132],"frozen,":[133],"retains":[136],"196":[137],"tokens.":[139],"Across":[140],"diverse":[141],"backbones,":[143,172],"yields":[145],"broad":[146],"gains":[147],"judge-assessed":[149],"correctness":[150,187],"reductions":[152],"hallucination":[154],"severity":[155],"single-encoder":[157],"interfaces":[158],"on":[159,189],"image":[160],"description":[161],"question":[164],"answering.":[165],"On":[166],"2B":[168],"9B":[170],"Qwen":[171],"compact":[174],"interface":[175],"outperforms":[176],"strongest":[178],"evaluated":[179],"or":[181],"token-compression":[182],"baselines":[183],"by":[184],"about":[185],"2.9":[186],"points":[188],"average.":[190]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}