ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation

• URL: http://arxiv.org/abs/2605.30484v1
• Date: Thu, 28 May 2026 19:03:30 GMT
• Title: ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation
• Abstract summary: Vision-Language-Action (VLA) models have shown promise for robotic manipulation, yet most existing policies reactively by directly regressing actions from current observations.<n>We propose ELAN4D, an embodiment-centric, 4D-aware training framework that enhances policies with future robot key tracks as predictive-temporal supervision.
• Score: 63.617951135459016
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language-Action (VLA) models have shown promise for robotic manipulation, yet most existing policies operate reactively by directly regressing actions from current observations, without explicitly modeling future dynamics. This limits their ability to generalize under out-of-distribution perturbations. To address this issue, we propose ELAN4D, an embodiment-centric, 4D-aware training framework that enhances VLA policies with future robot keypoint tracks as predictive spatio-temporal supervision. Using only forward kinematics from proprioceptive states, we derive 3D displacement tracks of robot keypoints, such as joints and the end-effector, with negligible preprocess cost. These tracks provide metric and compact supervision without requiring external trackers or reconstruction. A plug-and-play auxiliary branch with a lightweight track decoder injects this 4D signal into the action expert while preserving the pretrained vision-language backbone through gradient isolation. The track decoder is discarded during inference, leaving the base policy interface unchanged. Extensive experiments on LIBERO, LIBERO-Plus, RoboTwin2.0 and real-world manipulation tasks demonstrate that ELAN4D consistently improves over strong VLA baselines, achieving the best overall performance and substantial gains under out-of-distribution perturbations, including camera, background, and layout shifts. These results highlight the effectiveness of embodiment-centric 4D supervision for building more robust and generalizable manipulation policies.

Related papers

• Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation [76.16065370700488]
  We introduce Lift3D-VLA, a unified VLA framework that equips models with explicit 3D point cloud reasoning and enables temporally coherent action generation.<n>We show that Lift3D-VLA achieves 10.8% and 11.1% higher mean success rates on MetaWorld and RLBench than the best-performing prior VLA methods.
  arXiv  Detail & Related papers  (2026-07-07T17:59:47Z)
• WAM4D: Fast 4D World Action Model via Spatial Register Tokens [52.16661403052964]
  We present WAM4D, a fast 4D world action model that uses lightweight spatial register tokens as training-time future-depth readouts.<n>We show that WAM4D improves spatial consistency and achieves competitive action prediction while maintaining efficient inference.
  arXiv  Detail & Related papers  (2026-06-12T02:49:34Z)
• $μ_0$: A Scalable 3D Interaction-Trace World Model [54.38434730157622]
  We present a scalable world model based on 3D traces.<n>Our TraceExtract system automatically extracts 3D supervision.<n>These results establish 3D traces as a scalable and transferable representation for cross-embodiment manipulation.
  arXiv  Detail & Related papers  (2026-06-11T17:59:56Z)
• Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving [22.824000058639125]
  Envision4D is a fully self-supervised feed-forward framework for pose-free future extrapolation.<n>Future Pose Prediction module infers future camera parameters via an iterative denoising process.<n>In-layer Temporal Attention and Conditioned Motion Lifting transform the highly uncertain extrapolation process into robust mappings.
  arXiv  Detail & Related papers  (2026-06-09T10:04:38Z)
• From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data [71.22409934108924]
  Human videos are abundant and capture rich interactions, providing diverse semantic and physical cues for real-world manipulation.<n>This survey provides a unified view of how human videos are transformed into effective knowledge for Vision-Language-Action (VLA) models.<n>We highlight three key open challenges in this area: structuring unstructured videos into training-ready episodes, grounding video-derived supervision into robot-executable actions under embodiment and viewpoint heterogeneity, and designing evaluation protocols that better predict real-world deployment performance and transfer efficiency.
  arXiv  Detail & Related papers  (2026-05-18T06:19:16Z)
• Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representation [58.21084913574353]
  We introduce Pri4R, a simple approach that endows VLA models with an implicit understanding of world dynamics.<n>Pri4R augments VLA with a lightweight point track head that predicts 3D point tracks.<n>We show that 3D point track prediction is an effective supervision target for learning action-world dynamics.
  arXiv  Detail & Related papers  (2026-03-02T07:23:53Z)
• MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation [27.70398018267795]
  This work proposes a novel embodied 4D world model that enables geometrically consistent, arbitrary-view RGBD generation.<n>Experiments on three datasets demonstrate strong performance on both 4D scene generation and downstream manipulation.
  arXiv  Detail & Related papers  (2026-02-10T15:19:17Z)
• GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation [47.471097712217386]
  Existing approaches typically follow either a Vision-to-Action (V-A) paradigm, predicting actions directly from visual inputs, or a Vision-to-3D-to-Action (V-3D-A) paradigm, leveraging intermediate 3D representations.<n>In this paper, we adopt a V-4D-A framework that enables direct action reasoning from motion-aware 4D representations via a Gaussian Action Field (GAF)<n>Experiments demonstrate significant improvements, with achieving +11.5385 dB PSNR, +0.3864 SSIM and -0.5574 LPIPS improvements in reconstruction quality, while boosting the average +7.3% success
  arXiv  Detail & Related papers  (2025-06-17T02:55:20Z)
• Easi3R: Estimating Disentangled Motion from DUSt3R Without Training [69.51086319339662]
  We introduce Easi3R, a simple yet efficient training-free method for 4D reconstruction.<n>Our approach applies attention adaptation during inference, eliminating the need for from-scratch pre-training or network fine-tuning.<n>Our experiments on real-world dynamic videos demonstrate that our lightweight attention adaptation significantly outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-31T17:59:58Z)
• Street Gaussians without 3D Object Tracker [84.89933388445185]
  Most existing methods rely on labor-intensive manual labeling of object poses.<n>We propose a stable object tracking module by leveraging associations from 2D deep trackers within a 3D object fusion strategy.<n>We address inevitable tracking errors by further introducing a motion learning strategy in an implicit feature space that autonomously corrects trajectory errors and recovers missed detections.
  arXiv  Detail & Related papers  (2024-12-07T05:49:42Z)

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.