arXiv:2608.24885v1 Announce Type: cross Abstract: Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on a...
arXiv:2602. 13977v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision--Language--Action (VLA) models, but its requirement for massive real-world interaction prevents direct deployment on physical robots.
arXiv:2609.38059v1 Announce Type: cross Abstract: Real-world robot learning is constrained by the cost of collecting experience and evaluating candidate behaviors. Video generation models offer a sca...
SyncWorld is an action‑conditioned world model that functions as a zero‑shot simulator across unseen environments without additional training. It uses a visual calibration episode—paired frames and actions that expose all controllable degrees of freedom—to define a setup‑specific Action‑Visual Mapping in context. By training with these calibration contexts, the model learns to interpret actions through visual evidence and to leverage interaction history when explicit calibration is unavailable, enabling accurate simulation of action outcomes and test‑time policy improvement.
The paper introduces a reinforcement learning post‑training scheme that trains robot world models on their own autoregressive rollouts, using a contrastive RL objective adapted from diffusion models. It also proposes a training protocol that compares multiple variable‑length futures, a multi‑view visual fidelity reward, and demonstrates state‑of‑the‑art rollout fidelity on the DROID dataset, outperforming baselines on LPIPS, SSIM, and human preference tests.
arXiv:2606. 12217v1 Announce Type: cross Abstract: World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution before producing control actions.
DreamTrue is a multi‑view, cross‑embodiment robot world model that predicts physically plausible videos while faithfully following actions. It overcomes calibration and limited interaction coverage issues by rendering action trajectories into image‑space conditions, applying offline geometric calibration, and using counterfactual post‑training to generate a broader range of future videos. A human‑annotated defect dataset trains a video reward model that guides reinforcement‑learning post‑training, resulting in state‑of‑the‑art action following on AgiBot and a significant drop in interaction defect rates.
The survey "World-Action Models for Robot Learning and Control" reviews recent advances in coupling future world prediction with executable action generation for robots in open environments. It clarifies the scope of World-Action Models (WAMs) relative to conventional world models, model-based RL, and Vision‑Language‑Action policies, and organizes existing methods through a unified taxonomy covering representations, transition modeling, action interfaces, architectures, training pipelines, data modalities, and scaling strategies. The paper also surveys applications in manipulation, navigation, and autonomous driving, summarizes datasets, benchmarks, and metrics, and discusses key challenges such as action alignment, spatial consistency, long‑horizon memory, and efficient inference.
World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution before producing control actions. However, our empirical observations reveal a phenomenon: generating plausible visual futures does not always guarantee the extraction of accurate actions.
The paper introduces a Latent World Model (LWM) for robot navigation that predicts action‑conditioned latent feature compatibility instead of reconstructing future observations. By exploiting the correlation between spatial proximity and latent feature similarity, the model evaluates action consequences directly in latent space and supports counterfactual training using sampled action sequences. The learned world model can supervise policy learning from unlabeled video and further improve policies via reinforcement learning entirely within the model, eliminating the need for action annotations and additional environment interaction.
arXiv:2609.36851v1 Announce Type: new Abstract: End-to-end autonomous driving policies are commonly trained via imitation learning on logged demonstrations without observing the consequences of their...
World models enable agents to reason about future outcomes and learn policies from their knowledge of state transition, but existing approaches primarily focus on reconstructing future observations or...