AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

• URL: http://arxiv.org/abs/2606.09811v1
• Date: Mon, 08 Jun 2026 17:55:18 GMT
• Title: AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing
• Abstract summary: We propose AHA-WAM, an Asynchronous Horizon-Adaptive World-Action Model built on a dual Diffusion Transformer (DiT) architecture.<n>We show that AHA-WAM achieves state-of-the-art performance without any robot-data pretraining, attaining 92.80% average success on RoboTwin and 78.3% success across 4 real-world tasks.
• Score: 45.6226084109777
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World-action models have emerged as a promising paradigm for robot manipulation, jointly modeling visual scene dynamics and actions to inject physical priors into policy learning. However, existing world-action models couple world prediction and action execution at the same temporal resolution, forcing the world branch to model near-term frame variations that are redundant and weakly informative. We posit that strictly binding world prediction and action execution to the same temporal rhythm may underutilize the potential of the video branch for embodied control. Therefore, we propose AHA-WAM, an Asynchronous Horizon-Adaptive World-Action Model built on a dual Diffusion Transformer (DiT) architecture that reorganizes world-action modeling around this temporal asymmetry. AHA-WAM instantiates the video DiT as a low-frequency world planner that maintains rolling key-value memory over past observations and exposes reusable layerwise latent context encoding long-horizon scene evolution, while a high-frequency action DiT executes short action chunks in closed loop by querying this context through layerwise joint attention. To support asynchronous execution, we introduce horizon-adaptive offset training and Observation-Guided Video-Context Routing (OVCR), which together let the action expert exploit long-horizon world context while remaining responsive to real-time execution state without rerunning the video DiT. Experiments on RoboTwin and real-world manipulation tasks show that AHA-WAM achieves state-of-the-art performance without any robot-data pretraining, attaining 92.80% average success on RoboTwin and 78.3% success across 4 real-world tasks, while reaching 24.17 Hz closed-loop control with a 4.59x speedup over Fast-WAM.

Related papers

• StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models [84.17128030384099]
  StreamPI is a streaming multimodal temporal modeling framework.<n>It equips single-frame VLA with temporal reasoning capability without introducing any additional parameters.<n> Experiments on real-robot tasks spanning memory-dependent and precise perception scenarios, as well as the simulation benchmark LIBERO, demonstrate that StreamPI outperforms pi0.5 across diverse tasks.
  arXiv  Detail & Related papers  (2026-08-26T17:33:19Z)
• DynamicWAM: Dual-Path Motion Conditioning for World-Action Models in Dynamic Manipulation [7.0603285861926715]
  DynamicWAM is a compact WAM for dynamic object manipulation with dual-path motion conditioning.<n>On DOMINO, DynamicWAM achieves a 38.2% success rate and a 53.2 manipulation score, outperforming all evaluated baselines.
  arXiv  Detail & Related papers  (2026-08-01T17:49:39Z)
• 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)
• ABot-M0.5: Unified Mobility-and-Manipulation World Action Model [27.262271208923995]
  ABot-M0.5 is built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency.<n> Experiments on challenging mobile and fine-grained manipulation benchmarks demonstrate that ABot-M0.5 achieves state-of-the-art performance in both long-horizon task success and finegrained control accuracy.
  arXiv  Detail & Related papers  (2026-07-01T09:21:20Z)
• Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation [55.42006264038458]
  Action-conditioned world models have emerged as a promising paradigm for robot learning.<n>Mem-World is a memory-augmented multi-view action-conditioned world model.<n>We present W-VMem, a 4D wrist-view-centered surfel-indexed memory that anchors historical observations to temporally evolving surface elements.
  arXiv  Detail & Related papers  (2026-06-17T11:42:00Z)
• 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)
• HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models [58.191567345416836]
  World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics.<n>HarmoWAM fully leverages a world model to unify predictive and reactive control, enabling both general transit and precise manipulation.<n>We construct three training-unseen test environments across six real-world robotic tasks, covering variations in background, position, and object semantics.
  arXiv  Detail & Related papers  (2026-05-11T17:59:56Z)
• Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising [22.899605451385824]
  We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruction) in a single framework.<n>To leverage the strong visual priors of pretrained video diffusion models, X-WAM imagines the future world by predicting multi-view RGB-D videos.<n>Asynchronous Noise Sampling (ANS) to jointly optimize generation quality and action decoding efficiency.
  arXiv  Detail & Related papers  (2026-04-29T14:01:54Z)
• SPIRAL: A Closed-Loop Framework for Self-Improving Action World Models via Reflective Planning Agents [135.00390535239129]
  We introduce SPIRAL, a self-improving planning and iterative reflective action world modeling framework.<n> SPIRAL formulates ActWM as a closed-loop think-act-reflect process, where generation proceeds step by step under explicit planning and feedback.<n> Experiments across multiple TI2V backbones demonstrate consistent gains on ActWM-Bench and mainstream video generation benchmarks.
  arXiv  Detail & Related papers  (2026-03-09T14:00:36Z)
• Chain of World: World Model Thinking in Latent Motion [24.24061036481793]
  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.
  arXiv  Detail & Related papers  (2026-03-03T17:52:06Z)
• TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Model [53.555353366322464]
  We present TeleWorld, a real-time multimodal 4D world modeling framework that unifies video generation, dynamic scene reconstruction, and long-term world memory within a closed-loop system.<n>Our approach achieves seamless integration of dynamic object modeling and static scene representation within a unified 4D framework, advancing world models toward practical, interactive, and computationally accessible synthesis systems.
  arXiv  Detail & Related papers  (2025-12-31T18:31:46Z)
• MinD: Learning A Dual-System World Model for Real-Time Planning and Implicit Risk Analysis [32.08769443927576]
  We propose Manipulate in Dream (MinD), a dual-system world model for real-time, risk-aware planning.<n>MinD uses two asynchronous diffusion processes: a low-frequency visual generator (LoDiff) that predicts future scenes and a high-frequency diffusion policy (HiDiff) that outputs actions.<n>Our key insight is that robotic policies do not require fully denoised frames but can rely on low-resolution latents generated in a single denoising step.<n>MinD achieves a 63% success rate on RL-Bench, 60% on real-world Franka tasks, and operates at 11.3 FPS
  arXiv  Detail & Related papers  (2025-06-23T17:59:06Z)

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.