X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models

• URL: http://arxiv.org/abs/2605.25044v1
• Date: Sun, 24 May 2026 12:41:34 GMT
• Title: X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
• Abstract summary: 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.
• Score: 39.033717938466246
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning universal policies from cross-embodied data remains a fundamental challenge in robotics. Although Vision-Language-Action (VLA) models are pre-trained on large and diverse datasets, they typically rely on embodiment-specific fine-tuning to achieve strong performance in downstream tasks. This requirement severely limits their generalization capability and restricts knowledge transfer across embodiments performing similar tasks. To overcome these limitations, we focus on cross-embodied settings with shared robotic bases and heterogeneous end-effectors, and propose X-DiffVLA, a diffusion-based VLA model featuring a unified cross-embodied action head. X-DiffVLA can leverage the generative strengths of diffusion models to capture both the diversity and latent correlations in cross-embodied datasets. Specifically, we introduce Embodiment Forcing, a classifier-free guidance technique to implicitly steer action generation toward embodiment-specific functional components, capturing fine-grained structural nuances without explicit supervision. In addition, a Morphological Tree Diffusion approach is designed to strengthen behavioral correlations across diverse end-effectors, maximizing the transferability of heterogeneous demonstrations. Experimental results across RoboCasa and Isaac Gym, covering different embodiments from grippers to dexterous hands, show that X-DiffVLA achieves state-of-the-art performance, with improvements of 15.3% and 12.5%, respectively. Real-world evaluations further validate the robustness of the proposed framework and its effectiveness in scalable cross-embodied policy learning.

Related papers

• SCAR: Self-Supervised Continuous Action Representation Learning [36.917304453471864]
  We propose SCAR, a joint inverse-forward dynamics framework for learning unified action representations across embodiments from visual transitions.<n>Built on a pretrained generative backbone, SCAR uses an inverse dynamics model (IDM) to infer latent actions from latent observation pairs and a forward dynamics model (FDM) to predict future dynamics conditioned on them.<n>Experiments on the Procgen and Robotwin dataset show that the learned unified latent action representation serves as a stronger conditioning interface for world modeling than embodiment-specific raw actions.
  arXiv  Detail & Related papers  (2026-05-13T16:23:11Z)
• Adaptor: Advancing Assistive Teleoperation with Few-Shot Learning and Cross-Operator Generalization [26.90003783245582]
  Adaptor is a framework for robust cross-operator intent recognition.<n>It bridges the domain gap through two stages: preprocessing and policy learning.<n>It achieves state-of-the-art performance, improving success rates and efficiency over baselines.
  arXiv  Detail & Related papers  (2026-04-10T16:19:43Z)
• Cross-Hand Latent Representation for Vision-Language-Action Models [49.32460749933983]
  Training reliable vision-language-action models for dexterous manipulation requires large-scale demonstrations across many robotic hands.<n>We introduce XL-VLA, a vision-language-action framework integrated with a unified latent action space shared across diverse dexterous hands.
  arXiv  Detail & Related papers  (2026-03-10T18:50:57Z)
• 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)
• 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)
• Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy [73.75271615101754]
  We present Dita, a scalable framework that leverages Transformer architectures to directly denoise continuous action sequences.<n>Dita employs in-context conditioning -- enabling fine-grained alignment between denoised actions and raw visual tokens from historical observations.<n>Dita effectively integrates cross-embodiment datasets across diverse camera perspectives, observation scenes, tasks, and action spaces.
  arXiv  Detail & Related papers  (2025-03-25T15:19:56Z)

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.