PlayWorld learns high-fidelity robot world models from unsupervised self-play, producing physically consistent video predictions that outperform models trained on human data and enabling 65% better real-world policy performance via model-based RL.
Learning real-world action-video dynamics with het- erogeneous masked autoregression
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
EgoDex delivers the largest egocentric dataset with native 3D hand tracking for dexterous manipulation, enabling imitation learning policies for hand trajectory prediction on 194 tasks.
Step Forcing lets a 4-step video world model generate 30-second closed-loop rollouts, and a VLM judge scores them to reproduce the real RoboArena policy ranking at r=0.989.
A factorized modular diffusion policy improves fitting of multimodal robot actions and enables flexible task adaptation without catastrophic forgetting.
Survey organizing world models for robotic manipulation into representation families, a functional taxonomy, and infrastructure roles across pretraining, post-training, and inference, while reviewing 34 datasets and evaluation protocols.
citing papers explorer
-
PlayWorld: Learning Robot World Models from Autonomous Play
PlayWorld learns high-fidelity robot world models from unsupervised self-play, producing physically consistent video predictions that outperform models trained on human data and enabling 65% better real-world policy performance via model-based RL.
-
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
-
EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
EgoDex delivers the largest egocentric dataset with native 3D hand tracking for dexterous manipulation, enabling imitation learning policies for hand trajectory prediction on 194 tasks.
-
RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation
Step Forcing lets a 4-step video world model generate 30-second closed-loop rollouts, and a VLM judge scores them to reproduce the real RoboArena policy ranking at r=0.989.
-
Flexible Multitask Learning with Factorized Diffusion Policy
A factorized modular diffusion policy improves fitting of multimodal robot actions and enables flexible task adaptation without catastrophic forgetting.
-
World Models for Robotic Manipulation: A Survey
Survey organizing world models for robotic manipulation into representation families, a functional taxonomy, and infrastructure roles across pretraining, post-training, and inference, while reviewing 34 datasets and evaluation protocols.