[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82882-en":3,"doc-seo-82882-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},82882,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Qantara Bridge-Flow Training for Multi-Paradigm JEPA Control","Joint-Embedding Predictive Architectures (JEPAs) for control from raw pixels typically commit during training to a single inference paradigm, either trajectory optimisation in a learned dynamics model or direct behaviour cloning. Qantara introduces an end-to-end JEPA that unifies these options by combining Brownian-bridge interpolation between consecutive clean latents on the state axis with noise-to-data flow matching on the action axis. A single checkpoint supports multiple inference modes without retraining, achieving strong control and new SOTA on OGBench-Cube and competitive performance on Push-T and Cube under matched compute.","arXiv :2607 .04978v 1 [ cs .LG] 6 Jul 2026  \nQantara: Bridge-Flow Training for Multi-Paradigm JEPA Control  \nRuslan Rakhimov∗ George Bredis Yuriy Maksyuta Daniil Gavrilov  \nT-Tech  \nAbstract  \nJoint-Embedding Predictive Architectures (JEPAs) underpin a growing family of latent world models for control from raw pixels, but every existing JEPA world model commits at training time to a single inference paradigm: either trajectory optimisation in a learned dynamics model, or direct behaviour cloning. A single checkpoint that serves both would defer this choice to inference, when deployment constraints (rollout cost, observation accessibility) determine which path wins.  \nWe present Qantara, an end-to-end JEPA whose joint training objective pairs a Brownian-bridge interpolant between consecutive clean latents on the state axis with noise-to-data flow matching on the action axis. The same checkpoint serves three inference paradigms without retraining: latent planning, behaviour-cloning action sampling, and inverse dynamics, which we query through a video–inverse composition that first predicts the next latent without action conditioning, then extracts the action. Training concentrates mass on the edges of the (action-time, state-time) noise square, where inference queries the predictor: replacing it with uniform interior sampling drops Push-T planning from 90.1 to 53.3 SR at matched compute. On the LeWM control suite, Qantara reaches a 91.2 SR three-train-seed average and sets new SOTA on OGBench-Cube (+7 .7 SR over DINO-WM, +19 .7 over LeWM) . From the same weights, the behaviour-cloning and video–inverse paths reach 82–83 SR on Push-T and 71–73 SR on Cube. These results move JEPA world models from single-paradigm planners to multi-paradigm controllers.  \n1 Introduction  \nA robot deployed for visuomotor control faces inference-time constraints (per-step latency, the size of the action search space, whether a goal observation can be supplied) that the training run cannot anticipate. The same learned predictor is useful in different ways under different constraints: rolled out as a forward dynamics simulator under a planner when the search budget allows, or read off asa behaviour-cloning policy when latency is tight. Every JEPA world model trained from pixels for control today commits to one of these inference paradigms at training time, and a checkpoint trained for one cannot serve the others without retraining.  \nTwo clusters of prior work tile the relevant design space. Sub-billion JEPA world models commit to a single inference paradigm: PLDM [36], DINO-WM [42], and LeWM [29, 4] train action-conditional latent dynamics and plan via trajectory optimisation, while V-JEPA-2-AC [3] post-trains a 300M action head on a 1B video JEPA for direct behaviour cloning. Multi-paradigm checkpoints exist in a second cluster that operates in pixel space at billion-class scale: PAD, UVA, UWM, DUST, and Cosmos Policy [16, 22, 43, 39, 21] denoise observations and actions jointly and serve forward dynamics, inverse dynamics, and behaviour policy from one set of weights. The (sub-billion JEPA, multi-paradigm) cell is empty.  \n∗ Correspondence: [ru.rakhimov@t-tech.dev](ru.rakhimov@t-tech.dev. Project page:)[. Project page:](ru.rakhimov@t-tech.dev. Project page:) [https://corl-team.github.io/qantara](https://corl-team.github.io/qantara)  \nAccepted at ICML 2026 Workshop on Decision-Making from Offline Datasets to Online Adaptation: Black-Box Optimization to Reinforcement Learning.  \n\n| Training |  |  |  |  |  |  |\n| --- | --- | --- | --- | --- | --- | --- |\n|  | action latent state noised | v1 ẑ0 va0 ẑ1 va2 ẑ3 va3 ẑ4 vaT−1 ẑT\u003Cbr>  action head  latent head  \u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr> |  |  |  |  |\n|  |  | clean context noisy inputs |  |  |  |  |\n|  |  |  |  |  | \u003Cbr>o3 |  |\n\n\n| Edge-aligned (τa, τz) sampling |  |\n| --- | --- |\n| τz | \u003Cbr>\u003Cbr> |\n|  | τa |\n\nFigure 1: Qantara training and edge-aligned (τa ,τ z ) sampling. Left: block-causal predictor on (a, z) tokens; ","cbCaitMYat0MKDJs","https://ap.wps.com/l/cbCaitMYat0MKDJs","pdf",2760640,2,1,16,"English","en",105,"# Introduction\n## Motivation: inference-time constraints\n## Prior work clusters\n## Qantara approach and objective","[{\"question\":\"What problem does Qantara address in JEPA-based control models?\",\"answer\":\"Existing JEPA world models are trained for one inference paradigm, so a checkpoint cannot serve planning and imitation-style control without retraining. Qantara targets this deployment-time mismatch by enabling multiple inference paradigms from one checkpoint.\"},{\"question\":\"How does Qantara’s training objective combine state and action modeling?\",\"answer\":\"Qantara pairs a Brownian-bridge interpolant between consecutive clean latents on the state axis with noise-to-data flow matching on the action axis. It also samples per-token noise levels along edge-aligned modes to match inference queries.\"},{\"question\":\"Which inference paradigms can use the same trained Qantara checkpoint?\",\"answer\":\"The same weights support latent planning, behaviour-cloning action sampling, and inverse dynamics via a video–inverse composition. This lets the model defer the planning-vs-imitation choice to inference under deployment constraints.\"}]",1784183640,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"qantara-bridge-flow-training-for-multi-paradigm-jepa-control","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/qantara-bridge-flow-training-for-multi-paradigm-jepa-control/82882/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Qantara address in JEPA-based control models?","Question",{"text":75,"@type":76},"Existing JEPA world models are trained for one inference paradigm, so a checkpoint cannot serve planning and imitation-style control without retraining. Qantara targets this deployment-time mismatch by enabling multiple inference paradigms from one checkpoint.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Qantara’s training objective combine state and action modeling?",{"text":80,"@type":76},"Qantara pairs a Brownian-bridge interpolant between consecutive clean latents on the state axis with noise-to-data flow matching on the action axis. It also samples per-token noise levels along edge-aligned modes to match inference queries.",{"name":82,"@type":73,"acceptedAnswer":83},"Which inference paradigms can use the same trained Qantara checkpoint?",{"text":84,"@type":76},"The same weights support latent planning, behaviour-cloning action sampling, and inverse dynamics via a video–inverse composition. This lets the model defer the planning-vs-imitation choice to inference under deployment constraints.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]