Chain of World: World Model Thinking in Latent Motion

• URL: http://arxiv.org/abs/2603.03195v1
• Date: Tue, 03 Mar 2026 17:52:06 GMT
• Title: Chain of World: World Model Thinking in Latent Motion
• Abstract summary: Vision-Language-Action (VLA) models often overlook the predictive and temporal-causal structure underlying visual dynamics.<n>We introduce CoWVLA, a new "Chain of World" paradigm that unifies world-model temporal reasoning with a disentangled latent motion representation.<n>CoWVLA outperforms existing world-model and latent-action approaches and achieves moderate computational efficiency.
• Score: 24.24061036481793
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models are a promising path toward embodied intelligence, yet they often overlook the predictive and temporal-causal structure underlying visual dynamics. World-model VLAs address this by predicting future frames, but waste capacity reconstructing redundant backgrounds. Latent-action VLAs encode frame-to-frame transitions compactly, but lack temporally continuous dynamic modeling and world knowledge. To overcome these limitations, we introduce CoWVLA (Chain-of-World VLA), a new "Chain of World" paradigm that unifies world-model temporal reasoning with a disentangled latent motion representation. First, a pretrained video VAE serves as a latent motion extractor, explicitly factorizing video segments into structure and motion latents. Then, during pre-training, the VLA learns from an instruction and an initial frame to infer a continuous latent motion chain and predict the segment's terminal frame. Finally, during co-fine-tuning, this latent dynamic is aligned with discrete action prediction by jointly modeling sparse keyframes and action sequences in a unified autoregressive decoder. This design preserves the world-model benefits of temporal reasoning and world knowledge while retaining the compactness and interpretability of latent actions, enabling efficient visuomotor learning. Extensive experiments on robotic simulation benchmarks show that CoWVLA outperforms existing world-model and latent-action approaches and achieves moderate computational efficiency, highlighting its potential as a more effective VLA pretraining paradigm. The project website can be found at https://fx-hit.github.io/cowvla-io.

Related papers

• Native Video-Action Pretraining for Generalizable Robot Control [77.59831077077176]
  LingBot-VA 2.0 is a video-action foundation model built from the ground up for embodiment.<n>To meet the demands of high-frequency inference, our model employs a sparse MoE backbone.<n>Real-world deployment validates LingBot-VA 2.0 as a robust foundation model.
  arXiv  Detail & Related papers  (2026-07-09T16:15:43Z)
• DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation [41.032627534378065]
  We present Disentangled Video Generation World Model (DVG-WM), an efficient framework that decomposes world modeling into dynamics learning and visual synthesis.<n> Experiments on LIBERO and real-world platforms demonstrate improved video quality with up to 3.97 times acceleration.
  arXiv  Detail & Related papers  (2026-06-30T17:54:32Z)
• X-Foresight: A Joint Vision-Action Causal Forecasting Network via Predictive World Modeling [47.54820149491433]
  We introduce X-Foresight, a predictive world model integrated directly into the Vision-Language-Action architecture.<n>By predicting semantically distant chunks rather than adjacent frames, X-Foresight escapes trivial extrapolation.<n> Comprehensive experiments demonstrate that X-Foresight significantly outperforms VLA baselines in planning performance.
  arXiv  Detail & Related papers  (2026-05-24T06:37:04Z)
• DiLA: Disentangled Latent Action World Models [11.259992289079534]
  Latent Action Models (LAMs) enable the learning of world models from unlabeled video.<n>LAMs face a fundamental trade-off between action abstraction and generation fidelity.<n>We introduce DiLA, a novel Disentangled Latent Action world model that aims to resolve this trade-off via content-structure disentanglement.
  arXiv  Detail & Related papers  (2026-05-15T08:22:37Z)
• RotVLA: Rotational Latent Action for Vision-Language-Action Model [54.22746299071677]
  We introduce RotVLA, a VLA framework built on a continuous rotational latent action representation.<n>Latent actions are modeled as elements of SO(n), providing continuity, compositionality, and structured geometry aligned with real-world action dynamics.<n>RotVLA consists of a VLM backbone and a flow-matching action head, pretrained on large-scale cross-embodiment robotic datasets and human videos.
  arXiv  Detail & Related papers  (2026-05-13T11:58:02Z)
• Learning Vision-Language-Action World Models for Autonomous Driving [15.103497388527943]
  Vision-Language-Action (VLA) models have recently achieved notable progress in end-to-end autonomous driving.<n>VLA models often lack explicit modeling of temporal dynamics and global world consistency.<n>We present VLA-World, a simple yet effective VLA world model that unifies predictive imagination with reflective reasoning.
  arXiv  Detail & Related papers  (2026-04-10T07:38:05Z)
• DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA [72.9197085473598]
  DIAL is a framework bridging high-level decision making and low-level motor execution through a differentiable latent intent bottleneck.<n>A VLM-based System-2 performs latent world modeling by latent visual foresight within the VLM's native feature space.<n>A lightweight System-1 policy then decodes this predicted intent together with the current observation into precise robot actions.
  arXiv  Detail & Related papers  (2026-03-31T15:02:27Z)
• FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model [73.03346643967309]
  We argue that effective joint visuomotor predictive modeling requires both temporal continuity and visually-conditioned supervision decoupling.<n>FutureVLA is designed to extract joint visuomotor embeddings by first decoupling visual and motor information.<n>In the post-training stage, we employ a latent embeddings alignment strategy, enabling diverse downstream VLA models to internalize these temporal priors.
  arXiv  Detail & Related papers  (2026-03-11T12:39:55Z)
• Causal World Modeling for Robot Control [56.31803788587547]
  Video world models provide the ability to imagine the near future by understanding the causality between actions and visual dynamics.<n>We introduce LingBot-VA, an autoregressive diffusion framework that learns frame prediction and policy execution simultaneously.<n>We evaluate our model on both simulation benchmarks and real-world scenarios, where it shows significant promise in long-horizon manipulation, data efficiency in post-training, and strong generalizability to novel configurations.
  arXiv  Detail & Related papers  (2026-01-29T17:07:43Z)
• CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos [73.51386721543135]
  We propose Contrastive Latent Action Pretraining (CLAP), a framework that aligns the visual latent space from videos with a proprioceptive latent space from robot trajectories.<n>CLAP maps video transitions onto a quantized, physically executable codebook.<n>We introduce a dual-formulation VLA framework offering both CLAP-NTP, an autoregressive model excelling at instruction following and object generalization, and CLAP-RF, a Rectified Flow-based policy designed for high-frequency, precise manipulation.
  arXiv  Detail & Related papers  (2026-01-07T16:26:33Z)
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs [5.109732854501585]
  We introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations.<n>Our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.
  arXiv  Detail & Related papers  (2025-12-17T18:47:31Z)
• Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation [41.993197533574126]
  Inferix is an inference engine to enable immersive world synthesis through optimized semi-autoregressive decoding processes.<n>Inferix further enhances its offering with interactive video streaming and profiling, enabling real-time interaction and realistic simulation.
  arXiv  Detail & Related papers  (2025-11-25T01:45:04Z)
• Can World Models Benefit VLMs for World Dynamics? [59.73433292793044]
  We investigate the capabilities when world model priors are transferred into Vision-Language Models.<n>We name our best-performing variant Dynamic Vision Aligner (DyVA)<n>We find DyVA to surpass both open-source and proprietary baselines, achieving state-of-the-art or comparable performance.
  arXiv  Detail & Related papers  (2025-10-01T13:07:05Z)
• Seeing Space and Motion: Enhancing Latent Actions with Spatial and Dynamic Awareness for VLA [21.362682837521632]
  Latent Action Models (LAMs) enable Vision- Language-Action systems to learn semantic action rep- resentations from large-scale unannotated data.<n>We propose Farsighted-LAM, a latent action framework with geometry- aware spatial encoding and multi-scale temporal modeling.<n>We further propose SSM-VLA, an end- to-end VLA framework built upon Farsighted-LAM, which integrates structured perception with a visual Chain-of-Thought module.
  arXiv  Detail & Related papers  (2025-09-30T13:41:43Z)
• 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)
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge [41.030494146004806]
  We propose DreamVLA, a novel VLA framework that integrates comprehensive world knowledge forecasting to enable inverse dynamics modeling.<n>DreamVLA introduces a dynamic-region-guided world knowledge prediction, integrated with the spatial and semantic cues, which provide compact yet comprehensive representations for action planning.<n>Experiments on both real-world and simulation environments demonstrate that DreamVLA achieves 76.7% success rate on real robot tasks.
  arXiv  Detail & Related papers  (2025-07-06T16:14:29Z)
• Epona: Autoregressive Diffusion World Model for Autonomous Driving [39.389981627403316]
  Existing video diffusion models struggle with flexible-length, long-horizon predictions and integrating trajectory planning.<n>This is because conventional video diffusion models rely on global joint distribution modeling of fixed-length frame sequences.<n>We propose Epona, an autoregressive world model that enables localized distribution modeling.
  arXiv  Detail & Related papers  (2025-06-30T17:56:35Z)
• FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving [19.81442567260658]
  We propose a visual-temporalT framework that enables VLAs to think in images.<n>On nuScenes and NAVSIM, FSDrive improves accuracy and reduces collisions.
  arXiv  Detail & Related papers  (2025-05-23T09:55:32Z)
• Generative Pre-trained Autoregressive Diffusion Transformer [74.25668109048418]
  GPDiT is a Generative Pre-trained Autoregressive Diffusion Transformer.<n>It unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis.<n>It autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics.
  arXiv  Detail & Related papers  (2025-05-12T08:32:39Z)
• CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models [89.44024245194315]
  We introduce a method that incorporates explicit visual chain-of-thought (CoT) reasoning into vision-language-action models (VLAs)<n>We introduce CoT-VLA, a state-of-the-art 7B VLA that can understand and generate visual and action tokens.<n>Our experimental results demonstrate that CoT-VLA achieves strong performance, outperforming the state-of-the-art VLA model by 17% in real-world manipulation tasks and 6% in simulation benchmarks.
  arXiv  Detail & Related papers  (2025-03-27T22:23:04Z)

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.