{"id":"https://openalex.org/W7225577304","doi":"https://doi.org/10.20944/preprints202611.0781.v1","title":"From Laya to Vega: Open Non-Autoregressive Decision Models with Calibrated Probabilities","display_name":"From Laya to Vega: Open Non-Autoregressive Decision Models with Calibrated Probabilities","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225577304","doi":"https://doi.org/10.20944/preprints202611.0781.v1"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202611.0781.v1","doi":"https://doi.org/10.20944/preprints202611.0781.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0781.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202611.0781.v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116129664","display_name":"M Nandakishor","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nandakishor M","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5161263205","display_name":"Anjali M","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Anjali M","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161263205"],"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/T10028","display_name":"Topic Modeling","score":0.41670000553131104,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.41670000553131104,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.2101999968290329,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.07819999754428864,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/laya","display_name":"laya","score":0.6869999766349792},{"id":"https://openalex.org/keywords/vega","display_name":"Vega","score":0.9549999833106995},{"id":"https://openalex.org/keywords/policy-gradient-reinforcement-learning","display_name":"policy gradient reinforcement learning","score":0.6399999856948853},{"id":"https://openalex.org/keywords/strictly-proper-scoring-rules","display_name":"strictly proper scoring rules","score":0.8980000019073486},{"id":"https://openalex.org/keywords/energy-landscape","display_name":"energy landscape","score":0.4259999990463257},{"id":"https://openalex.org/keywords/boltzmann-sampling","display_name":"Boltzmann sampling","score":0.800000011920929},{"id":"https://openalex.org/keywords/symplectic-dynamics","display_name":"symplectic dynamics","score":0.7129999995231628},{"id":"https://openalex.org/keywords/conformal-prediction","display_name":"conformal prediction","score":0.7960000038146973},{"id":"https://openalex.org/keywords/abstention","display_name":"abstention","score":0.7440000176429749},{"id":"https://openalex.org/keywords/out-of-distribution-detection","display_name":"out-of-distribution detection","score":0.968999981880188},{"id":"https://openalex.org/keywords/open-source-ai","display_name":"open-source AI","score":0.3190000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5918999910354614},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4203000068664551},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C187819001","wikidata":"https://www.wikidata.org/wiki/Q187665","display_name":"Thermostat","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C201236551","wikidata":"https://www.wikidata.org/wiki/Q7310809","display_name":"Relative value","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2637999951839447},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C110639684","wikidata":"https://www.wikidata.org/wiki/Q20702","display_name":"Pendulum","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20944/preprints202611.0781.v1","doi":"https://doi.org/10.20944/preprints202611.0781.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0781.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202611.0781.v1","doi":"https://doi.org/10.20944/preprints202611.0781.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0781.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7225377778","https://openalex.org/W7221754031","https://openalex.org/W7225570622","https://openalex.org/W7223018858","https://openalex.org/W7222317577","https://openalex.org/W7214024689","https://openalex.org/W7214038975","https://openalex.org/W7224091991","https://openalex.org/W7220422788","https://openalex.org/W7222441141"],"abstract_inverted_index":{"Many":[0],"production":[1],"AI":[2],"pipelines":[3],"call":[4],"a":[5,19,24,27,46,51,56,73,87,98,109,148,157,187,191,207,211,219,227,244,287],"generative":[6],"language":[7,184],"model":[8,78,185],"for":[9],"decisions":[10],"that":[11,49,79,115,178],"need":[12],"no":[13],"text":[14],"at":[15],"all:":[16],"which":[17,156],"queue":[18],"ticket":[20],"belongs":[21,173],"to,":[22],"whether":[23],"prompt":[25],"is":[26,50,72,108,119,238],"jailbreak":[28],"attempt,":[29],"how":[30],"urgent":[31],"an":[32,153,182,222,261],"email":[33],"is.":[34],"The":[35,167,248],"answer":[36,237],"arrives":[37],"after":[38],"hundreds":[39],"of":[40,42,67,93,122,170,195],"milliseconds":[41],"token":[43,53],"sampling,":[44],"with":[45,102,221,282],"confidence":[47],"value":[48],"predicted":[52],"rather":[54],"than":[55],"measurement.":[57],"This":[58],"paper":[59,172],"documents":[60],"the":[61,120,123,161,171,176,216,236,269],"design,":[62],"mathematics":[63],"and":[64,132,147,189,225,233,235,260,267,298],"measured":[65],"record":[66],"two":[68,136],"open":[69],"alternatives.":[70],"Laya":[71],"421M":[74],"parameter":[75],"bidirectional":[76],"decision":[77,193],"answers":[80],"typed":[81],"questions":[82],"(choice,":[83],"score,":[84],"boolean)":[85],"about":[86],"state":[88],"in":[89,134,138,155,210,251,268],"one":[90,254,272],"forward":[91],"pass":[92],"roughly":[94],"33":[95],"ms":[96],"on":[97,164,200,253,291],"Tesla":[99],"T4,":[100],"trained":[101],"policy-gradient":[103],"reinforcement":[104],"learning":[105],"whose":[106],"reward":[107],"strictly":[110],"proper":[111],"scoring":[112],"rule,":[113],"so":[114],"honest":[116],"probability":[117],"reporting":[118],"optimum":[121],"objective;":[124],"it":[125],"went":[126],"from":[127,240,278],"plan":[128],"to":[129,174,197,280],"public":[130],"checkpoints":[131],"benchmarks":[133],"under":[135],"days":[137],"September":[139],"2026.":[140],"I":[141],"cover":[142],"its":[143,201],"architecture,":[144],"training":[145],"recipe":[146],"compact":[149],"results":[150],"record,":[151],"including":[152],"ablation":[154],"supervised":[158],"baseline":[159],"matches":[160],"RL":[162],"objective":[163],"single-step":[165],"questions.":[166],"larger":[168],"share":[169],"Vega,":[175],"architecture":[177],"followed.":[179],"Vega":[180],"freezes":[181],"instruction-tuned":[183],"as":[186,264],"reader":[188],"trains":[190,250],"dynamical":[192],"engine":[194,249,274],"14M":[196],"31M":[198],"parameters":[199],"hidden":[202],"states:":[203],"each":[204],"option":[205],"becomes":[206],"Gaussian":[208],"well":[209],"learned":[212],"64-dimensional":[213],"energy":[214],"landscape,":[215],"question":[217],"drops":[218],"particle":[220],"initial":[223],"position":[224],"momentum,":[226],"state-space":[228],"thermostat":[229],"sets":[230],"step":[231],"size":[232],"damping,":[234],"read":[239],"Boltzmann":[241],"occupancy":[242],"along":[243],"damped":[245],"symplectic":[246],"trajectory.":[247],"minutes":[252],"GPU,":[255],"carries":[256],"conformal":[257],"sets,":[258],"abstention":[259],"out-of-distribution":[262],"flag":[263],"fitted":[265],"artifacts,":[266],"vega-U":[270],"form":[271],"byte-identical":[273],"serves":[275],"four":[276],"readers":[277,284],"0.8B":[279],"27B,":[281],"new":[283],"attached":[285],"by":[286],"closed-form":[288],"port":[289],"fit":[290],"unlabelled":[292],"text.":[293],"All":[294],"weights,":[295],"code,":[296],"harnesses":[297],"known":[299],"failure":[300],"modes":[301],"are":[302],"public.":[303]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-11-09T00:00:00"}