Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage
cs.RO, cs.AI
Submitted: 2026-09-24
Updated: 2026-09-24
Comments: Submitted to the IEEE for possible publication. 12 pages, 14 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Challenges of Real-World Reinforcement Learning
- Mastering Diverse Domains through World Models
- Conditional Object-Centric Learning from Video
- Bridging the Gap to Real-World Object-Centric Learning
- ROOTS: Object-Centric Representation and Rendering of 3D Scenes
- Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views
- AquaJEPA: An Action-Conditioned Multimodal JEPA Family for Underwater Robot Dynamics
- Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- AdaJEPA: An Adaptive Latent World Model
- SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors
- Causal-JEPA: Learning World Models through Object-Level Latent Masking
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data
- DINOv3
- ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
- JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies