# Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control

arXiv: https://arxiv.org/abs/2607.04978 · HTML: https://mlsanity.com/paper/2607.04978/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 23 of 23)

- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Stochastic Interpolants: A Unifying Framework for Flows and Diffusions](https://mlsanity.com/paper/2303.08797/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)
- [LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels](https://mlsanity.com/paper/2603.19312/) (2026)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [OGBench: Benchmarking Offline Goal-Conditioned RL](https://mlsanity.com/paper/2410.20092/) (2024)
- [I2SB: Image-to-Image Schr"odinger Bridge](https://mlsanity.com/paper/2302.05872/) (2023)
- [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026)
- [Training Agents Inside of Scalable World Models](https://mlsanity.com/paper/2509.24527/) (2025)
- [RynnVLA-002: A Unified Vision-Language-Action and World Model](https://mlsanity.com/paper/2511.17502/) (2025)
- [What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?](https://mlsanity.com/paper/2512.24497/) (2025)
- [Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model](https://mlsanity.com/paper/2510.27607/) (2025)
- [World Models for Learning Dexterous Hand-Object Interactions from Human Videos](https://mlsanity.com/paper/2512.13644/) (2025)
- [Causal-JEPA: Learning World Models through Object-Level Latent Masking](https://mlsanity.com/paper/2602.11389/) (2026)
- [Value-guided action planning with JEPA world models](https://mlsanity.com/paper/2601.00844/) (2025)
- [OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation](https://mlsanity.com/paper/2505.20425/) (2025)

## Built on by (most cited first, 4 of 4)

- [Representation World Model: Learning States, Transition and Executable Plans in Representation](https://mlsanity.com/paper/2609.29171/) (2026)
- [AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control](https://mlsanity.com/paper/2609.30264/) (2026)
- [FlexiWorld: Learning and Planning via Flexible Action Chunks Across Multiple Time Scales](https://mlsanity.com/paper/2609.35138/) (2026)
- [Beyond a single latent space: a dual-latent world model for long-horizon planning](https://mlsanity.com/paper/2609.37644/) (2026)

## Abstract (arXiv)

Joint-Embedding Predictive Architectures (JEPAs) underpin a growing family of latent world models for control from raw pixels. Published JEPA world models for pixel-based control (PLDM, DINO-WM, LeWM, V-JEPA-2-AC) each commit at training time to a single inference paradigm, trajectory optimisation in a learned dynamics model, so a checkpoint trained to plan cannot be read off as a policy without retraining. Deferring that choice to inference would let the constraints that bind at deployment, per-step latency and whether a goal observation can be supplied, pick the path. We present Qantara, an end-to-end JEPA of about 21M parameters 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. One checkpoint serves three inference paradigms without retraining: latent planning, behaviour-cloning action sampling, and a video-inverse composition that predicts the next latent without action conditioning, then recovers the action bridging the two. Training samples the two noise levels along the edges of the (action-noise, state-noise) square, one edge per inference dispatch, so each path is trained where it is queried. Replacing that sampler with uniform sampling over the square at matched compute drops Push-T planning from 90.1 to 53.3 success rate (SR). On the LeWM control suite at a matched 10-epoch budget, Qantara averages 91.2 SR over the four environments and reaches 93.7 on OGBench-Cube, +7.7 over DINO-WM and +17.0 over LeWM, each measured against the stronger of that baseline's published score and our retrain of it. From the same weights the two goal-blind paths, which receive no goal image, reach 82.1-83.2 SR on Push-T and 70.8-72.8 on Cube at roughly 15-65x lower inference cost, and fall to near-noise on Reacher, whose released training corpus comes from a random policy.