DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation

• URL: http://arxiv.org/abs/2607.04927v1
• Date: Mon, 06 Jul 2026 10:57:01 GMT
• Title: DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation
• Abstract summary: World Action Models (WAMs) provide a promising alternative to Vision-Language-Action (VLA) policies.<n>Existing WAMs excel at physically grounded execution, but typically lack the explicit language-level planning interface.<n>We introduce DSWAM, a Dual-System World Action Foundation Model for fine-grained robot manipulation.
• Score: 14.193285862278913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World Action Models (WAMs) provide a promising alternative to Vision-Language-Action (VLA) policies by using video-based world modeling as dense supervision for robot action learning. Existing WAMs excel at physically grounded execution, but typically lack the explicit language-level planning interface in VLM-based VLAs for decomposing coarse instructions. Such decomposition becomes important when household tasks involve complex multi-step goals, where coarse user commands need to be converted into sequences of fine-grained executable subtasks. Meanwhile, the field still lacks a fair real-robot comparison between VLA and WAM execution capabilities, since existing systems often differ in data, robot embodiments, and task protocols. To address both the decomposition gap and the need for a controlled WAM-VLA comparison, we introduce DSWAM, a Dual-System World Action Foundation Model for fine-grained robot manipulation. DSWAM keeps a System 1 WAM executor as the default control path and optionally activates a System 2 vision-language subtask planner only when task decomposition is useful. The planner predicts executable subtasks from short-term visual history and a global task prompt, while the WAM executor performs world-aware action generation for each instruction or subtask. The executor is trained with action prediction and video co-training, but inference directly predicts action chunks without explicit future video generation. To make this execution path practical on real robots, we further integrate TensorRT acceleration, asynchronous execution, and real-time chunking (RTC) so that policy queries do not block robot control. To provide a fair real-robot comparison with VLA policies, we build and evaluate DSWAM under the DeMaVLA real-world deformable manipulation setting with matched robot platform, pretraining data, post-training data, and evaluation criteria.

Related papers

• $τ_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation [51.05516457377339]
  Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks.<n>We introduce $_0$-VLA, a hierarchical robot foundation model that formulates high-level subtask generation as a compute-scalable inference problem.<n>A low-level policy then executes the generated subtask across multiple robot embodiments.
  arXiv  Detail & Related papers  (2026-08-17T17:59:11Z)
• Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data [93.7685703383343]
  Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies is surprisingly difficult.<n>We argue that this gap can be bridged gradually with the right intermediate data.<n>We show that mixing task-relevant out-of-distribution ETC data with a small amount of action data enables the model to generalize to novel visual-language conditions.
  arXiv  Detail & Related papers  (2026-06-07T08:57:51Z)
• A Conversational Framework for Human-Robot Collaborative Manipulation with Distributed Generative AI models [0.0]
  This paper presents a distributed conversational framework for human-robot collaborative manipulation.<n>It integrates local language and vision-language models (VLMs) with a Robot Operating System 2 (ROS 2)-based execution stack.
  arXiv  Detail & Related papers  (2026-06-04T12:00:41Z)
• NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning [36.20611975009607]
  We introduce NovaPlan, a hierarchical framework that unifies closed-loop VLM and video planning.<n>At the high level, a VLM planner decomposes tasks into sub-goals and monitors robot execution in a closed loop.<n>To compute low-level robot actions, we extract and utilize both task-relevant object keypoints and human hand poses.
  arXiv  Detail & Related papers  (2026-02-23T18:35:18Z)
• Instruct2Act: From Human Instruction to Actions Sequencing and Execution via Robot Action Network for Robotic Manipulation [14.833622989644352]
  We develop a lightweight, fully on-device pipeline that converts natural-language commands into reliable manipulation.<n>Instruct2Act attains 91.5% sub-actions prediction accuracy while retaining a small footprint.<n>Results demonstrate that fine-grained instruction-to-action parsing, coupled with DATRN-based trajectory generation and vision-guided grounding, provides a practical path to deterministic, real-time manipulation.
  arXiv  Detail & Related papers  (2026-02-10T16:25:39Z)
• Robotic Control via Embodied Chain-of-Thought Reasoning [86.6680905262442]
  Key limitation of learned robot control policies is their inability to generalize outside their training data.<n>Recent works on vision-language-action models (VLAs) have shown that the use of large, internet pre-trained vision-language models can substantially improve their robustness and generalization ability.<n>We introduce Embodied Chain-of-Thought Reasoning (ECoT) for VLAs, in which we train VLAs to perform multiple steps of reasoning about plans, sub-tasks, motions, and visually grounded features before predicting the robot action.
  arXiv  Detail & Related papers  (2024-07-11T17:31:01Z)
• LLaRA: Supercharging Robot Learning Data for Vision-Language Policy [56.505551117094534]
  We introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations.<n>First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets.<n>We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control.
  arXiv  Detail & Related papers  (2024-06-28T17:59:12Z)
• Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks [54.60571399091711]
  Large Language Models (LLMs) have achieved impressive results in creating robotic agents for performing open vocabulary tasks. We present an interactive planning technique for partially observable tasks using LLMs.
  arXiv  Detail & Related papers  (2023-12-11T22:54:44Z)
• ProgPrompt: Generating Situated Robot Task Plans using Large Language Models [68.57918965060787]
  Large language models (LLMs) can be used to score potential next actions during task planning. We present a programmatic LLM prompt structure that enables plan generation functional across situated environments.
  arXiv  Detail & Related papers  (2022-09-22T20:29:49Z)

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.