VLMs excel at semantic and grouping tasks while VGMs are stronger on dense geometry and camera motion, with naive fusion yielding balanced representations.
hub
MotuBrain: An Advanced World Action Model for Robot Control
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
abstract
Vision-Language-Action (VLA) models generalize semantically well but often lack fine-grained modeling of world dynamics. We present MotuBrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation with a three-stream Mixture-of-Transformers architecture. A single model supports policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction, while scaling to heterogeneous multimodal data such as video-only, task-agnostic, and cross-embodiment robot data. Building on Motus, MotuBrain further introduces unified multiview modeling, an independent text stream for stronger language-action coupling, a shared cross-embodiment action representation, and an efficient post-training and deployment recipe for long-horizon real-world control. Our inference stack combines step reduction, compilation, FP8 quantization, DiT caching, V2A-style action-only inference, and real-time chunked closed-loop execution, achieving over 50x speedup over a naive baseline and up to 11 Hz inference. Experimentally, MotuBrain achieves 95.8% and 96.1% average success on RoboTwin 2.0 under clean and randomized settings, respectively, attains the strongest reported EWMScore in our WorldArena comparison, and adapts to new humanoid embodiments with only 50--100 trajectories. These results show that unified world action models can scale in generality, predictive accuracy, and real-world deployability.
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 11roles
background 1polarities
background 1representative citing papers
RepWAM introduces representation visual-action tokenizers to pretrain world action models that jointly model future visual states and latent actions under instructions for improved robot manipulation.
ω-EVA is a three-stage latent world model framework that trains action-conditioned dynamics, a language-conditioned flow policy, and a tri-branch refiner to improve embodied action generation in simulation.
LIBERO and CALVIN fail multiple proposed diagnostics for shortcut solvability, statistical significance, overfitting, and data dependence, while a tiny 0.09B probe reaches near-SOTA on LIBERO.
PAIWorld adds explicit geometric cross-view mechanisms and 3D distillation to DiT world models to achieve multi-view 3D consistency in robotic manipulation benchmarks.
Kairos is a native world model stack using cross-embodiment pretraining, hybrid linear temporal attention with theoretical error bounds, and deployment-aware co-design, reporting top performance on embodied benchmarks.
AGRA is an Action-Grounded Representation Alignment objective that aligns intermediate video diffusion features with semantic representations to make world action model hidden states more useful for low-level robot control, improving localization, affordance, and robustness.
HiMem-WAM integrates hierarchical latent actions and boundary-aware memory gates into world action models to enhance robustness and performance on memory-dependent long-horizon robotic tasks.
SANTS adaptively chooses denoising depth in video-based robot action diffusion policies using a state-dependent stopping hazard and noise ratio, trained via downstream action reward to reduce latency.
WALL-WM introduces event-grounded Vision-Language-Action pretraining that uses semantic events as the atomic unit to address granularity mismatch in world action models and reports state-of-the-art generalization.
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
citing papers explorer
-
$\omega$-EVA: Envision, Verify, and Act with Latent Interactive World Models
ω-EVA is a three-stage latent world model framework that trains action-conditioned dynamics, a language-conditioned flow policy, and a tri-branch refiner to improve embodied action generation in simulation.
-
PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation
PAIWorld adds explicit geometric cross-view mechanisms and 3D distillation to DiT world models to achieve multi-view 3D consistency in robotic manipulation benchmarks.
-
HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation
HiMem-WAM integrates hierarchical latent actions and boundary-aware memory gates into world action models to enhance robustness and performance on memory-dependent long-horizon robotic tasks.
-
SANTS: A State-Adaptive Scheduler for World Action Models
SANTS adaptively chooses denoising depth in video-based robot action diffusion policies using a state-dependent stopping hazard and noise ratio, trained via downstream action reward to reduce latency.
-
WALL-WM: Carving World Action Modeling at the Event Joints
WALL-WM introduces event-grounded Vision-Language-Action pretraining that uses semantic events as the atomic unit to address granularity mismatch in world action models and reports state-of-the-art generalization.
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.