DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation

• URL: http://arxiv.org/abs/2608.06374v1
• Date: Thu, 06 Aug 2026 17:59:20 GMT
• Title: DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation
• Abstract summary: DyPES-VLA is a cross-embodiment VLA that learns shared Dynamics Priors and Embodiment-Specific control.<n>As a generalist policy, our ourmethod achieves state-of-the-art performance across simulation and real-world evaluations.
• Score: 18.601805553878638
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models have become a powerful paradigm for robot manipulation, but training a single generalist policy for heterogeneous robot embodiments remains an open problem. Existing methods have two main limitations. First, they underuse dynamics priors shared across diverse visual and interaction data, limiting cross-embodiment transfer. Second, they require extensive manual preprocessing to convert embodiment-specific actions into a common format. To overcome these limitations, we propose DyPES-VLA, a cross-embodiment VLA that learns shared Dynamics Priors and Embodiment-Specific control. First, we learn shared dynamics priors by training the vision-language model (VLM) with a future-prediction objective on cross-embodiment data, driving the shared query representation to capture object motion, contact, and interaction-induced scene changes. Second, an embodiment-specific Mixture-of-Experts (MoE) action head translates these shared dynamics priors into executable controls directly in each embodiment's native action space, without manually pre-aligning heterogeneous actions into a common format. This head shares attention layers to capture common temporal action structures, while its embodiment-specific feed-forward experts resolve the unique kinematic constraints and control semantics of distinct embodiments. As a generalist policy, our \ourmethod achieves state-of-the-art performance across simulation and real-world evaluations, reaching 98.0% success on LIBERO, 59.25% on RoboCasa-GR1, and 89.02% on RoboTwin~2.0.

Related papers

• One Policy, Many Embodiments: Unified Camera-Centric Action Geometry Pre-training for Heterogeneous Embodied Manipulation [17.443768996704033]
  UCAG-P is a camera-centric unified action formulation that aligns heterogeneous embodied datasets into a shared geometric action space.<n>A geometry-conditioned action translator combines predicted motion with target-embodiment kinematics to produce executable controls.<n> UCAG-P is trained on 4.03K hours of robot and simulation data and 2.34K hours of human demonstrations.
  arXiv  Detail & Related papers  (2026-08-26T17:27:36Z)
• Learning Action Priors for Cross-embodiment Robot Manipulation [46.92215687389683]
  Most Vision-Language-Action (VLA) models build on a Vision-Language Model (VLM) backbone by attaching an action module and optimizing the full policy jointly.<n>This work proposes to pretrain the action module with motion priors before cross-modal VLA alignment.<n>We introduce a two-stage training framework that equips the action module with cross-embodiment temporal motion structure.
  arXiv  Detail & Related papers  (2026-06-24T17:59:56Z)
• Unified Motion-Action Modeling for Heterogeneous Robot Learning [35.20580699433655]
  UMA treats object motion and robot actions as co-evolving variables under a masked generative objective.<n>UMA enables multi-task pretraining across heterogeneous data sources without requiring manually annotated task instructions.<n>UMA consistently outperforms state-of-the-art baselines specialized for each inference mode.
  arXiv  Detail & Related papers  (2026-06-15T16:23:42Z)
• PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation [50.8450025321217]
  Vision-Language-Action (VLA) models offer a promising paradigm for generalist robotic policies.<n>We argue that these bottlenecks stem from the prevailing Direct Instruction-to-Control Mapping.<n>We propose PrimitiveVLA, a framework that shifts this paradigm toward a Primitive-Centric Disassemble & Assemble paradigm.
  arXiv  Detail & Related papers  (2026-05-27T15:41:18Z)
• X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models [39.033717938466246]
  We propose X-DiffVLA, a diffusion-based VLA model featuring a unified cross-embodied action head.<n>X-DiffVLA can leverage the generative strengths of diffusion models to capture both the diversity and latent correlations in cross-embodied datasets.<n>We show that X-DiffVLA achieves state-of-the-art performance, with improvements of 15.3% and 12.5%, respectively.
  arXiv  Detail & Related papers  (2026-05-24T12:41:34Z)
• Universal Pose Pretraining for Generalizable Vision-Language-Action Policies [83.39008378156647]
  Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency.<n>We propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors.<n>Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment.
  arXiv  Detail & Related papers  (2026-02-23T11:00:08Z)
• MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer [55.982504915794514]
  Cross-embodiment policies typically rely on shared-private architectures.<n>We introduce MOTIF for efficient few-shot cross-embodiment transfer.<n>We show that MOTIF significantly outperforms strong baselines in few-shot transfer scenarios.
  arXiv  Detail & Related papers  (2026-02-14T13:21:40Z)
• MiVLA: Towards Generalizable Vision-Language-Action Model with Human-Robot Mutual Imitation Pre-training [102.850162490626]
  We propose MiVLA, a vision-language-action model empowered by human-robot mutual imitation pre-training.<n>We show that MiVLA achieves strong improved generalization capability, outperforming state-of-the-art VLAs.
  arXiv  Detail & Related papers  (2025-12-17T12:59:41Z)
• HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies [83.41714103649751]
  Development of embodied intelligence models depends on access to high-quality robot demonstration data.<n>We present HiMoE-VLA, a novel vision-language-action framework tailored to handle diverse robotic data with heterogeneity.<n>HiMoE-VLA demonstrates a consistent performance boost over existing VLA baselines, achieving higher accuracy and robust generalizations.
  arXiv  Detail & Related papers  (2025-12-05T13:21:05Z)
• Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance [63.33213516925946]
  We introduce textbfAlign-Then-stEer (textttATE), a novel, data-efficient, and plug-and-play adaptation framework.<n>Our work presents a general and lightweight solution that greatly enhances the practicality of deploying VLA models to new robotic platforms and tasks.
  arXiv  Detail & Related papers  (2025-09-02T07:51:59Z)
• HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model [54.64088247291416]
  A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments.<n>Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction.<n>We introduce HybridVLA, a unified framework that absorbs the continuous nature of diffusion-based actions and the contextual reasoning of autoregression.
  arXiv  Detail & Related papers  (2025-03-13T17:59:52Z)

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.