{"id":"https://openalex.org/W7212001875","doi":"https://doi.org/10.48550/arxiv.2609.08333","title":"Fixed-Dimensional Latent Flow for Generating Variable-Size 3D Molecules","display_name":"Fixed-Dimensional Latent Flow for Generating Variable-Size 3D Molecules","publication_year":2026,"publication_date":"2026-09-08","ids":{"openalex":"https://openalex.org/W7212001875","doi":"https://doi.org/10.48550/arxiv.2609.08333"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.08333","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.08333","pdf_url":"https://arxiv.org/pdf/2609.08333","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/2609.08333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140634193","display_name":"Weichi Yao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Weichi","raw_affiliation_strings":["Michigan Institute for Data & AI in Society"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan Institute for Data & AI in Society","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011908450","display_name":"Cameron Gruich","orcid":"https://orcid.org/0000-0002-3801-1296","observed_orcids":["https://orcid.org/0000-0002-3801-1296"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gruich, Cameron","raw_affiliation_strings":["Department of Chemical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026770434","display_name":"Bryan R. Goldsmith","orcid":"https://orcid.org/0000-0003-1264-8018","observed_orcids":["https://orcid.org/0000-0003-1264-8018"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goldsmith, Bryan R.","raw_affiliation_strings":["Department of Chemical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140720176","display_name":"Yixin Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Yixin","raw_affiliation_strings":["Department of Statistics University of Michigan , Ann Arbor , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics University of Michigan , Ann Arbor , USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9473000168800354,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9473000168800354,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.035999998450279236,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10002","display_name":"Advanced Chemical Physics Studies","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/3d-molecular-generation","display_name":"3D molecular generation","score":0.847000002861023},{"id":"https://openalex.org/keywords/autoregressive-transformer","display_name":"autoregressive transformers","score":0.7860000133514404},{"id":"https://openalex.org/keywords/bond-reconstruction","display_name":"bond reconstruction","score":0.7620000243186951},{"id":"https://openalex.org/keywords/homo-lumo-gap","display_name":"HOMO-LUMO gap","score":0.9179999828338623},{"id":"https://openalex.org/keywords/molecular-design","display_name":"molecular design","score":0.5080000162124634}],"concepts":[{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.5152000188827515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5011000037193298},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4887000024318695},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.38830000162124634},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3693000078201294},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.08333","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.08333","pdf_url":"https://arxiv.org/pdf/2609.08333","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.2609.08333","doi":"https://doi.org/10.48550/arxiv.2609.08333","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.08333","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:2609.08333","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.08333","pdf_url":"https://arxiv.org/pdf/2609.08333","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":[{"id":"https://openalex.org/G2569205066","display_name":"Toward Automated Uncertainty Quantification in Causal Inference","funder_award_id":"2310831","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3335687950","display_name":"ACED: Tail-aware Generative Modeling for Inverse Discovery of Molecules","funder_award_id":"2435696","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G396568656","display_name":"Collaborative Research: ATD: Hawkes Process-Based Causal Relationship Discovery For Complex Threat Detection and Forecasting","funder_award_id":"2428059","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4406361865","display_name":"CAREER: Bringing Structure to the Unstructured: Robust Causal and Statistical Modeling of High-dimensional Unstructured Data","funder_award_id":"2440954","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8101864701","display_name":null,"funder_award_id":"N00014-23-1-2590","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333858","display_name":"Michigan Institute for Data Science, University of Michigan","ror":null},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212001875.pdf","grobid_xml":"https://content.openalex.org/works/W7212001875.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2105297930","https://openalex.org/W2295124130","https://openalex.org/W2529996553","https://openalex.org/W2798613236","https://openalex.org/W2808177712","https://openalex.org/W2889326414","https://openalex.org/W2965373594","https://openalex.org/W3024385728","https://openalex.org/W4386804497","https://openalex.org/W4389696354","https://openalex.org/W4396821495","https://openalex.org/W4400410081","https://openalex.org/W4400435053","https://openalex.org/W4406472463","https://openalex.org/W4411846484","https://openalex.org/W4412741697","https://openalex.org/W4413969676","https://openalex.org/W4415020523","https://openalex.org/W4415926518","https://openalex.org/W4416389179","https://openalex.org/W4417143695","https://openalex.org/W7083307393","https://openalex.org/W7119471711","https://openalex.org/W7131857144","https://openalex.org/W7140292008","https://openalex.org/W7148706124","https://openalex.org/W7155532689","https://openalex.org/W7162427155","https://openalex.org/W7168147234"],"related_works":["https://openalex.org/W7119471711","https://openalex.org/W7205314784","https://openalex.org/W7163923553","https://openalex.org/W4417143695","https://openalex.org/W7168147234","https://openalex.org/W7214728040","https://openalex.org/W4413969676","https://openalex.org/W7203696046","https://openalex.org/W4386467042","https://openalex.org/W7116738847"],"abstract_inverted_index":{"Molecular":[0],"size":[1,16],"is":[2],"intrinsically":[3],"linked":[4],"to":[5,25,52,136,157],"composition,":[6],"structure,":[7],"and":[8,47,59,65,86,91,100,103,120,142],"properties,":[9],"but":[10],"most":[11],"3D":[12],"molecular":[13,54,158],"generators":[14],"treat":[15],"as":[17,153],"a":[18,23,35,40,154],"predefined":[19],"input":[20],"rather":[21],"than":[22],"quantity":[24],"be":[26],"generated.":[27],"We":[28],"introduce":[29],"Equivariant-Free":[30],"Transformer-Autoencoded":[31],"Latent":[32],"Flow":[33],"Matching,":[34],"two-stage":[36],"framework":[37],"that":[38],"samples":[39],"fixed-dimensional":[41,147],"latent":[42,148],"vector":[43],"using":[44],"flow":[45],"matching":[46],"employs":[48],"an":[49],"autoregressive":[50,151],"Transformer":[51],"determine":[53],"size,":[55],"atom":[56,63],"types,":[57],"coordinates,":[58],"chemical":[60],"attributes.":[61],"Canonical":[62],"ordering":[64],"rigid-pose":[66],"alignment":[67],"enable":[68],"Transformers":[69],"without":[70,160],"equivariant":[71],"layers,":[72],"while":[73,138],"decoded":[74],"attributes":[75],"guide":[76],"bond":[77],"reconstruction.":[78],"On":[79],"PCQM4Mv2,":[80],"unconditional":[81],"generation":[82,149],"yields":[83],"87.9\\%":[84],"unique":[85],"novel":[87],"molecules":[88],"passing":[89],"sanitization":[90],"PoseBusters":[92],"checks,":[93],"exceeding":[94],"baselines":[95],"with":[96,150],"lower":[97],"end-to-end":[98,105],"training":[99],"sampling":[101],"time":[102],"higher":[104],"throughput.":[106],"Across":[107],"ten":[108],"target":[109,133],"HOMO-LUMO":[110],"gaps,":[111],"internal":[112],"ranking":[113],"retains":[114],"30\\%":[115],"of":[116,131],"the":[117,122,132],"screened":[118],"candidates":[119],"increases":[121],"density":[123],"functional":[124],"theory-verified":[125],"hit":[126],"rate":[127],"within":[128],"0.1":[129],"eV":[130],"from":[134],"25.0\\%":[135],"52.4\\%,":[137],"largely":[139],"preserving":[140],"novelty":[141],"diversity.":[143],"These":[144],"results":[145],"demonstrate":[146],"decoding":[152],"practical":[155],"approach":[156],"design":[159],"prespecifying":[161],"size.":[162]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-10T00:00:00"}