Cross-Embodiment Transfer via Behavior-Aligned Representations

• URL: http://arxiv.org/abs/2607.27549v1
• Date: Thu, 30 Jul 2026 00:49:53 GMT
• Title: Cross-Embodiment Transfer via Behavior-Aligned Representations
• Abstract summary: We study the role of using behavior-aligned representations in vision--action models to promote cross-embodiment transfer.<n>We develop a simulation-based benchmark designed to assess transfer with diverse cross-embodiment data to new embodiments.<n>We demonstrate that they can enhance sim-to-real cross-embodiment transfer, improving task completion progress of real robot policies pre-trained on simulation data by 28%.
• Score: 29.171887164748124
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress in large-scale imitation learning for robot manipulation has been driven by leveraging datasets across a wide range of robot embodiments. However, achieving significant cross-embodiment transfer is often still challenging. In this work, we study the role of using behavior-aligned representations (e.g., object bounding boxes, language motions, end-effector traces of robot motion) in vision-language-action (VLA) models to promote cross-embodiment transfer. We hypothesize that by possessing invariances across embodiments while being predictive of robot actions, these representations can help unify large-scale cross-embodiment data to enhance transfer. To assess our hypothesis, we develop a simulation-based benchmark designed to assess transfer with diverse cross-embodiment data to new embodiments. Using this benchmark, we compare different representations and ways of incorporating them. We identify that end-effector traces can be particularly beneficial for transfer, representations are generally more useful with larger prior datasets, and can be used to benefit from action-free data. We also demonstrate that they can enhance sim-to-real cross-embodiment transfer, improving task completion progress of real robot policies pre-trained on simulation data by 28%. We provide videos of our evaluations at our website: https://ajaysridhar.com/barx/.

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)
• Data Analogies Enable Efficient Cross-Embodiment Transfer [72.88252238231269]
  Generalist robot policies are trained on demonstrations collected across a wide variety of robots, scenes, and viewpoints.<n>We ask: what form of demonstration data is most useful for enabling transfer across robot set-ups?<n>Our simulated experiments show that while perceptual shifts such as viewpoint benefit most from broad diversity, morphology shifts benefit far less from unstructured diversity.
  arXiv  Detail & Related papers  (2026-03-06T16:42:46Z)
• 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)
• Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization [65.37179698521766]
  Vision-Language-Action (VLA) models show strong promise for generalist robot control.<n>It remains unclear whether -- and under what conditions -- the standard "scale data" recipe translates to robotics.<n>We present a systematic, controlled study of VLA scaling that revisits core training choices for pretraining across diverse robots.
  arXiv  Detail & Related papers  (2026-02-10T12:25:43Z)
• CEI: A Unified Interface for Cross-Embodiment Visuomotor Policy Learning in 3D Space [7.985647150826696]
  Cross-Embodiment Interface (CEI) is a framework for cross-embodiment learning.<n>CEI aligns robot trajectories through gradient-based optimization, followed by synthesizing observations and actions for unseen robot arms and end-effectors.<n>In experiments, CEI transfers data and policies from a Franka Panda robot to textbf16 different embodiments across textbf3 tasks in simulation.
  arXiv  Detail & Related papers  (2026-01-14T05:07:11Z)
• Trajectory Conditioned Cross-embodiment Skill Transfer [17.361383693716643]
  TrajSkill is a framework for Trajectory Conditioned Cross-embodiment Skill Transfer.<n>We show that TrajSkill reduces FVD by 39.6% and KVD by 36.6% compared with the state-of-the-art.
  arXiv  Detail & Related papers  (2025-10-09T04:26:06Z)
• Is Diversity All You Need for Scalable Robotic Manipulation? [50.747150672933316]
  We investigate the nuanced role of data diversity in robot learning by examining three critical dimensions-task (what to do), embodiment (which robot to use), and expert (who demonstrates)-challenging the conventional intuition of "more diverse is better"<n>We show that task diversity proves more critical than per-task demonstration quantity, benefiting transfer from diverse pre-training tasks to novel downstream scenarios.<n>We propose a distribution debiasing method to mitigate velocity ambiguity, the yielding GO-1-Pro achieves substantial performance gains of 15%, equivalent to using 2.5 times pre-training data.
  arXiv  Detail & Related papers  (2025-07-08T17:52:44Z)
• 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)
• Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation [62.22058066456076]
  Reinforcement Learning (RL) represents powerful tools to solve complex robotic tasks. RL does not work directly in the real-world, which is known as the sim-to-real transfer problem. We propose a method that learns on an observation space constructed by point clouds and environment randomization.
  arXiv  Detail & Related papers  (2020-07-27T17:46:59Z)

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.