SCAR: Self-Supervised Continuous Action Representation Learning

• URL: http://arxiv.org/abs/2605.16412v1
• Date: Wed, 13 May 2026 16:23:11 GMT
• Title: SCAR: Self-Supervised Continuous Action Representation Learning
• Abstract summary: 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.
• Score: 36.917304453471864
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the central role of action in embodied intelligence, learning transferable action representations from visual transitions remains a fundamental challenge, particularly when world models must generalize across embodiments under limited data. We argue that action is not merely an auxiliary conditioning signal, but a distinct representational factor that decouples the controllable change from embodiment-specific actuation. In this work, we propose SCAR, a joint inverse-forward dynamics framework for learning unified action representations across embodiments from visual transitions. 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. To make the latent space transferable rather than a generic visual bottleneck, we regularize the latent action posterior toward a standard Gaussian prior to limit arbitrary visual encoding, and introduce adversarial invariance to suppress embodiment- and environment-specific nuisance factors. 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, yielding improved cross-embodiment low-data adaptation and cross-task transfer. Taken together, these results suggest that action can be learned as a shared representation of controllable change across embodiments, providing an interface for more transferable and generalizable world models.

Related papers

• CAER: Causal Action Effect Reweighting for World Model Training [31.737118584204342]
  We introduce Causal Action Effect Reweighting (CAER), a training paradigm that redistributes supervision toward the tokens whose predicted future is causally affected by the action.<n>CAER contrasts the model's own predictions with and without action conditioning to localize these tokens online, then normalizes the resulting effect map into a weight that preserves the total coefficient mass and changes only where it is spent.<n> Experiments across heterogeneous action-conditioned world-model tasks show that CAER converges to better solutions than uniform MSE training, with consistent improvements in the physical consistency, controllability, and visual quality of generated videos
  arXiv  Detail & Related papers  (2026-08-31T14:49:56Z)
• Decoupling Intention from Trajectory: A Representational Deduction Framework for World Action Models [22.16380408116294]
  World Action Models (WAMs) aim to construct a unified architecture capable of understanding world state evolution and guiding to generative motion planning.<n>We propose PILOT, whose core Representational Deduction (RD) bridges this gap by integrating motion thought-of-chain guidance as a native model capability.
  arXiv  Detail & Related papers  (2026-08-07T09:12:15Z)
• Sensorimotor World Models: Perception for Action via Inverse Dynamics [59.121736411156384]
  We introduce a sensorimotor world model trained end-to-end with inverse dynamics regularization.<n>It prevents representation collapse and induces action-aligned representations.<n>It learns compact, interpretable latent spaces and enables competitive planning performance across simple 2D and 3D control tasks.
  arXiv  Detail & Related papers  (2026-06-18T11:25:16Z)
• CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization [15.232107188163747]
  We introduce CLAW, a framework for learning a world model jointly with continuous latent action representations directly from action-free videos.<n>We show that the resulting latent action world model supports both imitation learning from observation and goal-directed planning.
  arXiv  Detail & Related papers  (2026-06-02T18:40:24Z)
• HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models [58.191567345416836]
  World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics.<n>HarmoWAM fully leverages a world model to unify predictive and reactive control, enabling both general transit and precise manipulation.<n>We construct three training-unseen test environments across six real-world robotic tasks, covering variations in background, position, and object semantics.
  arXiv  Detail & Related papers  (2026-05-11T17:59:56Z)
• 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)
• \ extsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation [50.027425808733994]
  textscNaVIDA is a unified VLN framework that couples policy learning with action-grounded visual dynamics and adaptive execution.<n>textscNaVIDA augments training with chunk-based inverse-dynamics supervision to learn causal relationship between visual changes and corresponding actions.<n>Experiments show that textscNaVIDA achieves superior navigation performance compared to state-of-the-art methods with fewer parameters.
  arXiv  Detail & Related papers  (2026-01-26T06:16:17Z)
• 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)
• Diffusion Transformer Policy [48.50988753948537]
  We propose a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, to model continuous end-effector actions.<n>By leveraging the scaling capability of transformers, the proposed approach can effectively model continuous end-effector actions across large diverse robot datasets.
  arXiv  Detail & Related papers  (2024-10-21T12:43:54Z)
• ReCoRe: Regularized Contrastive Representation Learning of World Model [21.29132219042405]
  We present a world model that learns invariant features using contrastive unsupervised learning and an intervention-invariant regularizer. Our method outperforms current state-of-the-art model-based and model-free RL methods and significantly improves on out-of-distribution point navigation tasks evaluated on the iGibson benchmark.
  arXiv  Detail & Related papers  (2023-12-14T15:53:07Z)

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.