What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
在联合嵌入预测世界模型中成功因素是什么?
机构 * Meta FAIR ; Inria Paris(巴黎理工院) ; Ecole normale supérieure / PSL(巴黎高等师范学院 / PSL) ; New York University(纽约大学)
专题命中 具身推理 :world model(title,abstract);manipulation(abstract);navigation(abstract);robotic(abstract)
AI总结 本文研究了在物理规划中使用联合嵌入预测世界模型(JEPA-WMs)的成功因素,通过分析模型架构、训练目标和规划算法对规划成功的影响,提出了一种在导航和操作任务中优于现有基线方法的模型。
Comments V2 of the article: - Added AdaLN-zero - Added table comparing JEPA-WMs with baselines with std translating per-seed variability only, no variability across epochs - Reordered figures in main body of the paper V3: added data scaling experiments, theoretical appendix section on autoregressive rollout, acceptance at TMLR