Meta FAIR's RoboJEPA establishes first scaling law for multi-embodiment robot world models
ylecun · x · 2026-10-11
Meta FAIR、Mila 等机构联合推出 RoboJEPA,一个基于 JEPA 架构的机器人潜在世界模型,在覆盖 12 种机器人具身形态的大规模真实机器人数据集上训练,参数规模达 8B。
核心发现:
- 首个针对多具身机器人世界模型的 Scaling Law:潜在想象(latent rollout)误差随计算量呈二阶幂律下降,可外推预测更大规模模型的质量
- 想象误差与下游真实机器人规划性能强相关,可作为真机评测的可靠代理指标
- 潜在世界模型可零样本部署为机器人 agent:仅朝一个目标图像规划,即可完成需要长程规划的真实硬件任务
团队将开源全部模型 checkpoint、训练代码和机器人部署代码,号称是首个基于真实机器人数据建立的多具身世界模型 scaling law 工作。
More from Embodied
- China's BCI innovation enters fast track, early wins seen in assistive therapy and rehab — yogthos · 2026-10-11
- AgenticROS Cloud adds telepresence: turn a ROS 2 robot into your remote eyes, ears and AI agent — chrismatthieu · 2026-10-11
- Adding Flexi-Tac Touch Sensors to SO101 Robots Boosts Policy Convergence and Efficiency — k7agar · 2026-10-11
- Tesla Cybercab fleet hits 300+ vehicles in Austin, an 8x scale-up in one month — aelluswamy · 2026-10-11
- Qualcomm CEO predicts AI phone supercycle, smart glasses as top AI wearable — SuB8u · 2026-10-11
- WUJI Hand 2 nails pen-spinning dexterity via glove teleop and sim-to-real, open source — ChrisGPT · 2026-10-11