EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation

• URL: http://arxiv.org/abs/2608.02990v1
• Date: Tue, 04 Aug 2026 01:01:18 GMT
• Title: EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation
• Abstract summary: We present EmbodiedVAE, a novel video VAE that provides compact yet controllable latent representations tailored for robotic manipulation world models.<n>Our proposed EmbodiedVAE achieves superior reconstruction quality with high compression rate, while enabling more precise action control in robotic manipulation scenarios with an average of 2dB PSNR improvement over state-of-the-art video VAEs.
• Score: 35.20482569112933
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Latent diffusion models (LDMs) have recently significantly advanced embodied learning in constructing powerful embodied manipulation world models. However, despite the remarkable performance, existing LDMs predominantly rely on Variational Autoencoders (VAEs) optimized for natural scenes while failing to account for the unique characteristics of embodied manipulation scenarios, yielding latent representations that are neither compact nor controllable, thereby hindering efficient training of LDMs and precise robotic control. To solve this problem, we present EmbodiedVAE, a novel video VAE that provides compact yet controllable latent representations tailored for the robotic manipulation world models. Specifically, EmbodiedVAE adopts a dual-encoder, single-decoder architecture with an asymmetric spatio-temporal compression module, which automatically disentangles the robot arm's motion from background environment, resulting in overall compactness while providing explicit embodied latent to support fine-grained action control. To further preserve the temporal consistency of learned robotic motion latent, we introduce an optimal-transport-based consistency module that explicitly enforces motion fidelity and inter-frame coherence. Extensive experiments demonstrate that our proposed EmbodiedVAE achieves superior reconstruction quality with high compression rate, while enabling more precise action control in robotic manipulation scenarios with an average of 2dB PSNR improvement over state-of-the-art video VAEs.

Related papers

• LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments [41.26480439505561]
  World Action Models (WAMs) have emerged as a powerful paradigm for embodied intelligence.<n>Forcing models to reconstruct task-irrelevant visual details dissipates representational capacity and renders policies vulnerable to visual distractors.<n>We propose LeapBot-WA, which establishes a novel Predictive-Latent paradigm for WAMs by operationalizing the Joint-Embedding Predictive Architecture (JEPA) as a World-Anchor.
  arXiv  Detail & Related papers  (2026-07-27T03:36:45Z)
• Native Video-Action Pretraining for Generalizable Robot Control [77.59831077077176]
  LingBot-VA 2.0 is a video-action foundation model built from the ground up for embodiment.<n>To meet the demands of high-frequency inference, our model employs a sparse MoE backbone.<n>Real-world deployment validates LingBot-VA 2.0 as a robust foundation model.
  arXiv  Detail & Related papers  (2026-07-09T16:15:43Z)
• CT-VAM: A Cerebello-Thalamic-Inspired Vision-Action Model for Efficient Visuomotor Control [8.522323773053882]
  We propose a vision-action model (CT-VAM) for efficient task-conditioned visuomotor control.<n>CT-VAM acts as a compact local execution policy that predicts action chunks from dualview visual observations, proprioception, and a lightweight task condition.<n>With only 68M parameters, CT-VAM achieves LIBERO success rates competitive with substantially larger VLA models.
  arXiv  Detail & Related papers  (2026-06-08T14:46:43Z)
• DisCo: World Models with Discrete Camera Motion Control [79.86256515640231]
  We propose DisCo, a controllable video world model that conditions generation on a compact set of discrete action primitives to improve action separability.<n>DisCo achieves significantly more reliable action following while preserving visual quality.
  arXiv  Detail & Related papers  (2026-06-06T03:50:45Z)
• Strain-Parameterized Coupled Dynamics and Dual-Camera Visual Servoing for Aerial Continuum Manipulators [0.8594140167290097]
  Tendon-driven continuum aerial manipulators (TD-ACMs) combine the maneuverability of uncrewed aerial vehicles (UAVs) with the compliance of lightweight robots (CRs)<n>Existing continuum coupled dynamic modeling approaches for TD-ACMs incur high computational costs.<n>This paper presents a generalized dynamic formulation of a coupled TD-ACM with an underactuated base.
  arXiv  Detail & Related papers  (2026-03-24T15:33:22Z)
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs [5.109732854501585]
  We introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations.<n>Our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.
  arXiv  Detail & Related papers  (2025-12-17T18:47:31Z)
• OmniSAT: Compact Action Token, Faster Auto Regression [70.70037017501357]
  We introduce an Omni Swift Action Tokenizer, which learns a compact, transferable action representation.<n>The resulting discrete tokenization shortens the training sequence by 6.8$times$, and lowers the target entropy.
  arXiv  Detail & Related papers  (2025-10-08T03:55:24Z)
• FreeAction: Training-Free Techniques for Enhanced Fidelity of Trajectory-to-Video Generation [50.39748673817223]
  We introduce two training-free, inference-time techniques that fully exploit explicit action parameters in robot video generation.<n>First, action-scaled classifier-free guidance dynamically modulates guidance strength in proportion to action magnitude, enhancing controllability over motion intensity.<n>Second, action-scaled noise truncation adjusts the distribution of initially sampled noise to better align with the desired motion dynamics.
  arXiv  Detail & Related papers  (2025-09-29T03:30:40Z)
• Physical Autoregressive Model for Robotic Manipulation without Action Pretraining [65.8971623698511]
  We build upon autoregressive video generation models to propose a Physical Autoregressive Model (PAR)<n>PAR leverages the world knowledge embedded in video pretraining to understand physical dynamics without requiring action pretraining.<n>Experiments on the ManiSkill benchmark show that PAR achieves a 100% success rate on the PushCube task.
  arXiv  Detail & Related papers  (2025-08-13T13:54:51Z)
• Generative Pre-trained Autoregressive Diffusion Transformer [74.25668109048418]
  GPDiT is a Generative Pre-trained Autoregressive Diffusion Transformer.<n>It unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis.<n>It autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics.
  arXiv  Detail & Related papers  (2025-05-12T08:32:39Z)
• ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer [58.49950218437718]
  We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech.<n>The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding Regularization (DER) into a Vision Transformer (ViT) core architecture.<n>To enhance model robustness, we incorporate the proposed DER strategy, which equips the model with dual capabilities of noise resistance and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-03-27T16:39:40Z)

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.