Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training

• URL: http://arxiv.org/abs/2605.07288v1
• Date: Fri, 08 May 2026 05:54:33 GMT
• Title: Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training
• Abstract summary: One approach treats learned World Models as generative simulators, enabling policy optimization entirely within "imagination"<n>However, when deployed as simulators for specific environments such as the LIBERO benchmark, existing World Models often suffer from poor generalization and long-horizon error accumulation.<n>We propose Sword, a robust World Model framework, to mitigate these problems.
• Score: 19.013714390803052
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The integration of Vision-Language-Action (VLA) models with World Models has gained increasing attention. One representative approach treats learned World Models as generative simulators, enabling policy optimization entirely within "imagination." However, when deployed as simulators for specific environments such as the LIBERO benchmark, existing World Models often suffer from poor generalization and long-horizon error accumulation. During closed-loop rollouts, these models are highly sensitive to initial-state perturbations; minor changes in color, illumination, and other visual factors can trigger cascading hallucinations, leading to severe blurriness or overexposure. Moreover, long-horizon error accumulation further degrades the quality and fidelity of predicted future states. These issues limit the reliability of World Models as simulators. To mitigate these problems, we propose Sword, a robust World Model framework. Our method introduces Structure-Guided Style Augmentation to disentangle the visual textures of interactive environments from task-relevant dynamics, thereby improving generalization. We further propose Dynamic Latent Bootstrapping, which maintains consistency between training and inference while keeping memory consumption low. Extensive experiments on the LIBERO benchmark show that our method significantly outperforms the baseline WoVR in terms of generalization, generation quality, robustness, fidelity, and the success rate of reinforcement-learning post-training for VLA models.

Related papers

• Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models [35.944951371813296]
  Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction.<n>We propose VLA-MBPO, a practical framework to tackle these problems in VLA finetuning.<n>Our approach has three key design choices: (i) adapting unified multimodal models for data-efficient world modeling; (ii) an interleaved view decoding mechanism to enforce multi-view consistency; and (iii) chunk-level branched rollout to mitigate error compounding.
  arXiv  Detail & Related papers  (2026-03-21T02:44:39Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model [87.75549463328836]
  The goal of this paper is to improve the performance and reliability of vision-language-action (VLA) models through iterative online interaction.<n>We propose a simple iterative improvement algorithm that uses real-world roll-out data to improve the fidelity of the world model.<n>We achieve a 39.2% absolute success rate improvement over the base policy and 11.6% improvement from training with the generated synthetic rollouts.
  arXiv  Detail & Related papers  (2026-02-12T15:21:47Z)
• World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy [55.03832008486675]
  World-VLA-Loop is a closed-loop framework for the joint refinement of world models and Vision-Language-Action (VLA) policies.<n>We propose a state-aware video world model that functions as a high-fidelity interactive simulator by jointly predicting future observations and reward signals.
  arXiv  Detail & Related papers  (2026-02-06T08:57:55Z)
• Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation [18.67176370944511]
  Real-world dark images commonly exhibit not only low visibility and contrast but also complex noise and blur, posing significant restoration challenges.<n>We propose a generative framework based on visual autoregressive ( VAR) modeling, guided by perceptual priors from the vision-language model (VLM)<n>Our framework is fully unsupervised and achieves state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2025-11-23T19:08:45Z)
• WMPO: World Model-based Policy Optimization for Vision-Language-Action Models [22.01666177489494]
  Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation.<n>We introduce World-Model-based Policy Optimization (WMPO), a principled framework for on-policy VLA without interacting with the real environment.
  arXiv  Detail & Related papers  (2025-11-12T17:54:09Z)
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving [52.63591791507895]
  We propose textbfDriveVLA-W0, a training paradigm that employs world modeling to predict future images.<n>This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment.<n>Experiments on the NAVSIM v1/v2 benchmark and a 680x larger in-house dataset demonstrate that DriveVLA-W0 significantly outperforms BEV and VLA baselines.
  arXiv  Detail & Related papers  (2025-10-14T17:59:47Z)
• Learning Primitive Embodied World Models: Towards Scalable Robotic Learning [50.32986780156215]
  We propose a novel paradigm for world modeling--Primitive Embodied World Models (PEWM)<n>By restricting video generation to fixed short horizons, our approach enables fine-grained alignment between linguistic concepts and visual representations of robotic actions.<n>Our framework bridges the gap between fine-grained physical interaction and high-level reasoning, paving the way toward scalable, interpretable, and general-purpose embodied intelligence.
  arXiv  Detail & Related papers  (2025-08-28T14:31:48Z)
• Adapting World Models with Latent-State Dynamics Residuals [10.892848566977369]
  ReDRAW is a latent-state autoregressive world model pretrained in simulation and calibrated to target environments.<n>It enables RL agents to be optimized with imagined rollouts under corrected dynamics and then deployed in the real world.
  arXiv  Detail & Related papers  (2025-04-03T03:41:30Z)
• Pre-Trained Video Generative Models as World Simulators [59.546627730477454]
  We propose Dynamic World Simulation (DWS) to transform pre-trained video generative models into controllable world simulators.<n>To achieve precise alignment between conditioned actions and generated visual changes, we introduce a lightweight, universal action-conditioned module.<n> Experiments demonstrate that DWS can be versatilely applied to both diffusion and autoregressive transformer models.
  arXiv  Detail & Related papers  (2025-02-10T14:49:09Z)
• EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling [8.250616459360684]
  We introduce EDELINE, a unified world model architecture that integrates state space models with diffusion models.<n>Our approach outperforms existing baselines across visually challenging Atari 100k tasks, memory-demanding benchmark, and 3D first-person ViZDoom environments.
  arXiv  Detail & Related papers  (2025-02-01T15:49:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.