# Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage

arXiv: https://arxiv.org/abs/2609.30214 · HTML: https://mlsanity.com/paper/2609.30214/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 22 of its 58 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Challenges of Real-World Reinforcement Learning](https://mlsanity.com/paper/1904.12901/) (2019)
- [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)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control](https://mlsanity.com/paper/1812.00568/) (2018)
- [Bridging the Gap to Real-World Object-Centric Learning](https://mlsanity.com/paper/2209.14860/) (2022)
- [ROOTS: Object-Centric Representation and Rendering of 3D Scenes](https://mlsanity.com/paper/2006.06130/) (2020)
- [Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views](https://mlsanity.com/paper/2111.07117/) (2021)
- [Causal-JEPA: Learning World Models through Object-Level Latent Masking](https://mlsanity.com/paper/2602.11389/) (2026)
- [The Reality Gap in Robotics: Challenges, Solutions, and Best Practices](https://mlsanity.com/paper/2510.20808/) (2025)
- [AdaJEPA: An Adaptive Latent World Model](https://mlsanity.com/paper/2606.32026/) (2026)
- [ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model](https://mlsanity.com/paper/2603.22281/) (2026)
- [SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors](https://mlsanity.com/paper/2606.23444/) (2026)
- [Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning](https://mlsanity.com/paper/2608.18746/) (2026)
- [Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data](https://mlsanity.com/paper/2607.16314/) (2026)
- [Beyond Instance Slots: Semantically Rich World Models for Physical Interaction Planning](https://mlsanity.com/paper/2608.22294/) (2026)
- [AquaJEPA: An Action-Conditioned Multimodal JEPA Family for Underwater Robot Dynamics](https://mlsanity.com/paper/2607.29393/) (2026)
- [JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics](https://mlsanity.com/paper/2608.24044/) (2026)
- [Identifying Habit, Physics, and Nuisance in Robot World Models](https://mlsanity.com/paper/2609.09210/) (2026)

## Abstract (arXiv)

We present Underwater C3-JEPA (cross-view, control-conditioned, context-extended), an object-centric multi-view predictive world model for near-field heavy-load underwater ROV salvage. Without contact sensors, it predicts in latent space how the task-object state evolves through contact interaction and under the hydrodynamic lag of the vehicle, from synchronized multi-view RGB observations and vehicle control signals. C3-JEPA encodes multi-camera observations into task-object and context tokens, fuses cross-camera evidence through held-out-view attention, and directly predicts future states conditioned on control. Weak binding anchors the target and gripper at low annotation cost, while SIGReg sharpens the geometric representation. Experiments show that the learned representation transfers substantially more task-relevant information to downstream probes than a reconstruction-free latent baseline, while keeping the predictor lightweight. The resulting predictive interface supports model-predictive-control (MPC) candidate evaluation and imagined-rollout behavior-agent training. Validation on real underwater video shows the same architecture recovering a withheld camera's object state and staying ahead of persistence, so the recipe transfers beyond simulation.