Underwater C3-JEPA：面向 ROV 打捞的跨视角世界模型

它无需接触传感器，仅凭多相机 RGB 观测和载体控制信号，在潜空间预测抓取交互中任务物体的状态演化。模型通过 held-out-view attention 融合跨相机证据，用 weak binding 低成本绑定目标与夹爪，并用 SIGReg 强化几何表征。

实验显示其表征向下游探针迁移的任务相关信息显著多于无重建潜空间基线，且预测器保持轻量，可用于 MPC 候选评估和想象 rollout 的行为智能体训练。真实水下视频验证表明，同一架构能恢复被屏蔽相机视角下的物体状态并优于 persistence 预测。

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

We present Underwater C$^{3}$-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. C$^{3}$-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.

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：C3-JEPA、世界模型、机器人、MPC，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Yuncong Yang, Jinlong Li, Yulong Xue, Feng Wu, Chunwen Zhang, Lei Qiao, Xuyang Wang），经 AITOP 多维评分管线结构化提炼。