{"id":"https://openalex.org/W7224089946","doi":"https://doi.org/10.48550/arxiv.2610.37626","title":"Know, then Draw: A New Learning Paradigm for Visual Generation","display_name":"Know, then Draw: A New Learning Paradigm for Visual Generation","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224089946","doi":"https://doi.org/10.48550/arxiv.2610.37626"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.37626","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37626","pdf_url":"https://arxiv.org/pdf/2610.37626","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.37626","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160039996","display_name":"Yucheng Mao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mao, Yucheng","raw_affiliation_strings":["University of California , San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030551813","display_name":"Chongjian Ge","orcid":"https://orcid.org/0000-0003-1142-9171","observed_orcids":["https://orcid.org/0000-0003-1142-9171","https://orcid.org/0000-0003-2746-2216"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ge, Chongjian","raw_affiliation_strings":["University of California , San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001760915","display_name":"Zhuowen Tu","orcid":"https://orcid.org/0000-0002-1900-2124","observed_orcids":["https://orcid.org/0000-0002-1900-2124"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tu, Zhuowen","raw_affiliation_strings":["University of California , San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160003303","display_name":"Hao Tan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tan, Hao","raw_affiliation_strings":["University of California , San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076386225","display_name":"Hanwen Jiang","orcid":"https://orcid.org/0000-0002-1523-8551","observed_orcids":["https://orcid.org/0000-0002-1523-8551"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiang, Hanwen","raw_affiliation_strings":["University of California , San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.000699999975040555,"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/visual-generation","display_name":"visual generation","score":0.7680000066757202},{"id":"https://openalex.org/keywords/text-to-image-models","display_name":"text-to-image models","score":0.7799999713897705},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.6859999895095825},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"knowledge acquisition","score":0.8930000066757202},{"id":"https://openalex.org/keywords/semantic-knowledge","display_name":"semantic knowledge","score":0.45399999618530273},{"id":"https://openalex.org/keywords/pixel-diffusion","display_name":"pixel diffusion","score":0.45899999141693115},{"id":"https://openalex.org/keywords/semantic-tokenization","display_name":"semantic tokenization","score":0.5830000042915344},{"id":"https://openalex.org/keywords/scaling-laws","display_name":"scaling laws","score":0.7960000038146973},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.5649999976158142},{"id":"https://openalex.org/keywords/high-fidelity-rendering","display_name":"high-fidelity rendering","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789000272750854},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6625000238418579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6288999915122986},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6075000166893005},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41119998693466187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3707999885082245},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33709999918937683},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C56814567","wikidata":"https://www.wikidata.org/wiki/Q1323686","display_name":"Explicit knowledge","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25859999656677246}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.37626","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37626","pdf_url":"https://arxiv.org/pdf/2610.37626","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.2610.37626","doi":"https://doi.org/10.48550/arxiv.2610.37626","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.37626","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.37626","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37626","pdf_url":"https://arxiv.org/pdf/2610.37626","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224089946.pdf","grobid_xml":"https://content.openalex.org/works/W7224089946.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417077981","https://openalex.org/W4416052906","https://openalex.org/W4417461713","https://openalex.org/W4399554455","https://openalex.org/W4415097436","https://openalex.org/W6966724211","https://openalex.org/W7154483288","https://openalex.org/W7214014674","https://openalex.org/W7093078643","https://openalex.org/W7160095423"],"abstract_inverted_index":{"Visual":[0],"generation":[1,65,72],"requires":[2],"both":[3,60],"high-level":[4],"semantic":[5,81,89],"knowledge":[6,24,43,109],"and":[7,26,40,45,63,111,113,151,155],"fine-grained":[8],"pixel":[9,126],"details.":[10],"We":[11,67,103],"propose":[12],"a":[13,87,138],"learning":[14,61],"paradigm":[15,159],"that":[16,70,115],"assigns":[17],"these":[18],"roles":[19],"to":[20],"autoregressive":[21,116],"pretraining":[22,54,117],"for":[23,29,56,108],"acquisition":[25,44,110],"diffusion":[27,127],"post-training":[28],"high-fidelity":[30],"rendering.":[31,46],"Within":[32],"this":[33],"framework,":[34],"we":[35,136],"study":[36],"the":[37,52,119,134,157],"objective,":[38],"representation,":[39],"scaling":[41,106],"of":[42],"Controlled":[47],"comparisons":[48],"identify":[49],"autoregression":[50],"as":[51],"stronger":[53],"objective":[55],"downstream":[57],"rendering,":[58,112],"improving":[59],"efficiency":[62],"final":[64,79],"quality.":[66],"further":[68],"find":[69,114],"AR-only":[71],"quality":[73,82],"does":[74],"not":[75],"necessarily":[76],"correlate":[77],"with":[78,92,125,142],"performance;":[80],"matters":[83],"more.":[84],"This":[85],"motivates":[86],"purely":[88],"tokenizer":[90],"trained":[91,129],"language":[93],"supervision":[94],"alone,":[95],"without":[96],"an":[97],"image":[98],"decoder":[99],"or":[100],"reconstruction":[101],"loss.":[102],"establish":[104],"compute-optimal":[105],"laws":[107],"lowers":[118],"fitted":[120],"asymptotic":[121],"rendering":[122],"loss":[123],"compared":[124],"models":[128],"from":[130],"scratch.":[131],"Guided":[132],"by":[133],"laws,":[135],"train":[137],"3B-parameter":[139],"text-to-image":[140],"model":[141],"only":[143],"6,600":[144],"H100":[145],"GPU-hours,":[146],"achieving":[147],"86":[148],"on":[149,153],"GenEval":[150],"87":[152],"DPG-Bench":[154],"validating":[156],"proposed":[158],"at":[160],"scale.":[161]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-29T00:00:00"}