{"id":"https://openalex.org/W7161716717","doi":"https://doi.org/10.48550/arxiv.2605.18381","title":"Generating Physically Consistent Molecules with Energy-Based Models","display_name":"Generating Physically Consistent Molecules with Energy-Based Models","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7161716717","doi":"https://doi.org/10.48550/arxiv.2605.18381"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.18381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18381","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":"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.2605.18381","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136494478","display_name":"Christoph Griesbacher","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Griesbacher, Christoph","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075851161","display_name":"Lea Bogensperger","orcid":"https://orcid.org/0009-0005-5765-056X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bogensperger, Lea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030032319","display_name":"Andreas Habring","orcid":"https://orcid.org/0000-0002-1201-5782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Habring, Andreas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032205387","display_name":"Thomas Pock","orcid":"https://orcid.org/0000-0001-6120-1058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pock, Thomas","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/T11948","display_name":"Machine Learning in Materials Science","score":0.9401999711990356,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9401999711990356,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.010700000450015068,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.00800000037997961,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/metric","display_name":"Metric (unit)","score":0.6187999844551086},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.513700008392334},{"id":"https://openalex.org/keywords/energy-landscape","display_name":"Energy landscape","score":0.46810001134872437},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/artificial-noise","display_name":"Artificial noise","score":0.42239999771118164},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42010000348091125},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4016000032424927},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.3898000121116638},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3874000012874603}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.565500020980835},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.513700008392334},{"id":"https://openalex.org/C119621388","wikidata":"https://www.wikidata.org/wiki/Q5377166","display_name":"Energy landscape","level":2,"score":0.46810001134872437},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4490000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44119998812675476},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.42239999771118164},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C187653413","wikidata":"https://www.wikidata.org/wiki/Q7135015","display_name":"Parallel tempering","level":5,"score":0.3222000002861023},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C10803110","wikidata":"https://www.wikidata.org/wiki/Q1341441","display_name":"Force field (fiction)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.289000004529953},{"id":"https://openalex.org/C35304006","wikidata":"https://www.wikidata.org/wiki/Q5962","display_name":"Boltzmann constant","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.26489999890327454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.18381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18381","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":"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.2605.18381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18381","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":"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":[{"score":0.827630341053009,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Molecules":[0],"in":[1,57],"equilibrium":[2],"follow":[3],"a":[4,12,42,60,91,152],"Boltzmann":[5],"distribution,":[6],"making":[7],"the":[8,53,99,104,127,146],"underlying":[9],"energy":[10,54,100,148],"landscape":[11,149],"physically":[13],"grounded":[14],"modeling":[15],"objective.":[16,64],"However,":[17],"such":[18],"landscapes":[19],"are":[20],"difficult":[21],"to":[22,30,97,134],"learn":[23],"from":[24],"data":[25],"and,":[26],"once":[27],"learned,":[28],"hard":[29],"sample":[31],"from.":[32],"Diffusion":[33],"and":[34,50,115,117,140,158,161,173],"flow-matching":[35],"models":[36],"sidestep":[37],"these":[38],"difficulties":[39],"by":[40,77],"learning":[41,78],"time-conditional":[43],"score":[44],"or":[45],"transport":[46],"field":[47],"between":[48],"noise":[49],"data,":[51],"losing":[52],"inductive":[55,75],"bias":[56,76],"exchange":[58],"for":[59,107,121,130,156],"more":[61],"tractable":[62],"training":[63],"We":[65,102],"introduce":[66],"EBMol,":[67],"an":[68,79],"energy-based":[69],"model":[70],"(EBM)":[71],"that":[72,145],"restores":[73],"this":[74],"atom-additive":[80],"scalar":[81],"potential":[82,171],"without":[83,165],"explicit":[84],"simulation":[85],"during":[86],"training.":[87],"Our":[88],"method":[89],"employs":[90],"flow-inspired":[92],"Restoring":[93],"Field":[94],"Matching":[95],"objective":[96],"approximate":[98],"landscape.":[101],"adopt":[103],"Mirror-Langevin":[105],"algorithm":[106],"sampling,":[108],"enabling":[109],"unified":[110],"updates":[111],"of":[112],"atomic":[113],"positions":[114],"types,":[116],"incorporate":[118],"parallel":[119],"tempering":[120],"inference-time":[122],"compute":[123],"scaling.":[124],"EBMol":[125],"is":[126],"first":[128],"EBM":[129],"3D":[131],"molecular":[132],"generation":[133,164],"achieve":[135],"state-of-the-art":[136],"performance":[137],"on":[138],"QM9":[139],"GEOM-Drugs.":[141],"Moreover,":[142],"we":[143],"show":[144],"learned":[147],"serves":[150],"as":[151],"principled":[153],"quality":[154],"metric":[155],"ranking":[157],"filtering":[159],"configurations,":[160],"demonstrate":[162],"controllable":[163],"retraining":[166],"through":[167],"shape-steered":[168],"sampling":[169],"via":[170],"composition":[172],"zero-shot":[174],"linker":[175],"design.":[176]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-20T00:00:00"}