OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining

• URL: http://arxiv.org/abs/2609.07398v1
• Date: Mon, 07 Sep 2026 12:12:32 GMT
• Title: OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining
• Abstract summary: We introduce OpenWAM, an open research stack that turns world-action pretraining into a controlled experimental program.<n>OpenWAM-, an open WAM pretrained on roughly 6,400 hours of egocentric human and robot data, is evaluated across simulation and real-world benchmarks.
• Score: 65.60703573854387
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World-Action Models inherit world knowledge from video-generative priors, and channel it into executable control signals through embodied experience. Existing systems, however, are monolithic: the generative backbone, visual representation, architecture, information flow, inference procedure, and training data are tightly coupled, obscuring which design choices matter and why. We introduce OpenWAM, an open research stack that turns world-action pretraining into a controlled experimental program. OpenWAM-Infra factorizes the WAM design space into composable modules with unified training, inference, deployment, and evaluation. On this substrate, OpenWAM-Study examines three questions through controlled experiments: what to inherit, how world and action learning interact, and how their synergy scales; and distills three principles: upstream knowledge transfers through a sufficiently capable generative backbone and a compact, information-rich latent space; world-action synergy requires dedicated action capacity, explicit world-to-action information flow, and synchronized joint denoising; and embodied pretraining principally improves out-of-domain generalization, with one-stage co-training over egocentric and robot data integrating world coverage and action grounding. Composing these principles, we build OpenWAM-α, an open WAM pretrained on roughly 6,400 hours of egocentric human and robot data and evaluated across simulation and real-world benchmarks. Across the eight simulation benchmarks and the real-robot experiments, which together span embodiments from single-arm and bimanual manipulation to dexterous hands, OpenWAM-α delivers consistently excellent performance, sustaining its top-tier standing from simulation to the physical world. We release the full stack, including infrastructure, evaluation protocols, pretrained models, and data recipes, to facilitate future research.

Related papers

• World-Action Models for Robot Learning and Control: A Survey [41.45329550202786]
  Recent advances in world models, video generation, and Vision-Language-Action (VLA) policies have motivated the development of World-Action Models (WAMs)<n>This survey provides a robotics-oriented review of WAMs.<n>We clarify their scope relative to conventional world models, model-based reinforcement learning, action-conditioned video generation, and reactive VLA policies, and organize existing methods through a unified taxonomy.<n>We discuss key challenges in action alignment, world-action factorization, spatial and multi-view consistency, long-horizon memory, neural simulation for closed-loop policy learning, and efficient inference
  arXiv  Detail & Related papers  (2026-09-13T16:35:56Z)
• Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation [63.11032720821731]
  textitSAGE is a framework that enables agents to learn within a physics-grounded semantic abstraction rather than a photorealistic simulation.<n>We demonstrate that textitSAGE significantly improves planner-assisted embodied navigation, achieving a 53.21% LLM-Match Success Rate on A-EQA.
  arXiv  Detail & Related papers  (2026-05-11T07:34:30Z)
• daVinci-LLM:Towards the Science of Pretraining [58.6458452580545]
  daVinci-LLM combines industrial-scale resources with full research freedom to advance the science of pretraining.<n>We release complete data processing pipelines, full training processes, and systematic exploration results.
  arXiv  Detail & Related papers  (2026-03-28T07:00:49Z)
• Building Explicit World Model for Zero-Shot Open-World Object Manipulation [30.004607772330473]
  We propose an explicit-world-model-based framework for open-world manipulation.<n>The framework integrates open-set perception, digital-twin reconstruction, sampling and evaluation of interaction strategies.<n> Experimentally, the proposed framework is able to perform multiple open-set manipulation tasks without any task-specific action demonstrations.
  arXiv  Detail & Related papers  (2026-03-14T08:13:32Z)
• Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation [69.30586607892842]
  We introduce Genie Envisioner (GE), a unified world foundation platform for robotic manipulation.<n>GE integrates policy learning, evaluation, and simulation within a single video-generative framework.
  arXiv  Detail & Related papers  (2025-08-07T17:59:44Z)
• Detecting and Learning Out-of-Distribution Data in the Open world: Algorithm and Theory [15.875140867859209]
  This thesis makes contributions to the realm of machine learning, specifically in the context of open-world scenarios. Research investigates two intertwined steps essential for open-world machine learning: Out-of-distribution (OOD) Detection and Open-world Representation Learning (ORL)
  arXiv  Detail & Related papers  (2023-10-10T00:25:21Z)
• Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning [54.67880602409801]
  In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of visual control tasks. We introduce Contextualized World Models (ContextWM) that explicitly separate context and dynamics modeling. Our experiments show that in-the-wild video pre-training equipped with ContextWM can significantly improve the sample efficiency of model-based reinforcement learning.
  arXiv  Detail & Related papers  (2023-05-29T14:29:12Z)
• Bridging the Gap to Real-World Object-Centric Learning [66.55867830853803]
  We show that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric representations to arise in a fully unsupervised way. Our approach, DINOSAUR, significantly out-performs existing object-centric learning models on simulated data.
  arXiv  Detail & Related papers  (2022-09-29T15:24:47Z)

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.