The paper introduces P³-WAM, a unified world action model for egocentric dexterous manipulation that integrates 3D perception, action-conditioned prediction, and goal-directed planning. It operates in three modes—Perceive, Predict, and Plan—using a mixture-of-transformers architecture that shares base weights and adapts to modality-specific inputs. Experiments demonstrate that unified training improves performance across all three capabilities, outperforming specialized baselines on 3D hand reconstruction and action-conditioned video prediction while producing more instruction‑adherent manipulation videos.
arXiv:2609.22332v1 Announce Type: cross Abstract: Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act...
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
Video Prediction Policy 2 (VPP2) is a new world action model that improves zero‑shot generalization for both video prediction and action generation. It achieves this by pretraining a large, diverse manipulation video dataset with event‑level supervision, then distilling the model into a single‑step visual planner and adding a mixture‑of‑transformers action module. Experiments show VPP2 outperforms leading baselines on open‑ended video prediction, real‑world zero‑shot manipulation, and several challenging benchmarks.
arXiv:2610.02840v1 Announce Type: cross Abstract: World action models jointly learn to forecast world dynamics and predict robot actions, such that the learned internal world dynamics guide accurate...
arXiv:2610.20904v1 Announce Type: cross Abstract: Egocentric human videos offer a scalable alternative to costly robot demonstra- tions, yet transferring their manipulation priors to robot control re...
arXiv:2606. 10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots.
ZimaBlue is a scalable framework that learns generalizable World Action Models (WAMs) from large-scale egocentric videos. It follows a three-stage curriculum: causal video pre‑training, video‑action mid‑training with a unified action representation, and final specialization to a target robot. The system employs an asynchronous Slow‑Fast architecture to enable real‑time 30 Hz action prediction, achieving a jump in real‑robot zero‑shot success from 36.1% to 77.8% when leveraging over 120,000 hours of embodied video.
Generalizable robot manipulation requires policies that can anticipate how visual scenes evolve while executing language instructions. While recent Vision-Language-Action models benefit from large-scale pretraining, their predominantly static pretraining objectives provide limited supervision for physical dynamics and temporal causality, leaving control-relevant knowledge to be learned from downstream robot demonstrations.
Being‑M0.7 is a latent world‑action model that learns from a large mixed‑modality human dataset (over 10,000 hours of video‑only, motion‑only, and paired video‑motion data) to predict future latent visual states and motion. The model is pre‑trained on human data, adapted to robot viewpoints during mid‑training, and then combined with an action expert via gated cross‑attention during post‑training to produce executable whole‑body commands. In experiments, Being‑M0.7 outperforms baselines on the SIMPLE benchmark and matches the best baseline on real‑world Unitree G1 loco‑manipulation tasks.
arXiv:2608.22067v1 Announce Type: cross Abstract: World-Action Models (WAMs) build robot control on video-generation backbones, which jointly predict dense future visual trajectories and robot action...
World models offer a promising route toward robot planning by enabling agents to imagine and verify the consequences of actions before execution. However, current video-based world models often struggle to capture the physical constraints that govern manipulation, particularly contact.
DELE-w0.5 is a robotic manipulation framework that predicts future latent states instead of generating full video sequences, thereby inferring robot actions directly from these compact representations. By focusing on physical state changes rather than visual transitions, it reduces model complexity and inference latency. In 480 real‑robot trials across four long‑horizon tasks, DELE‑w0.5 achieved 62.5 % overall task success and 81.3 % macro ordered‑stage progress, outperforming the strongest baseline by 47.5 and 30.7 percentage points.