WAM4D: Fast 4D World Action Model via Spatial Register Tokens

• URL: http://arxiv.org/abs/2606.14048v1
• Date: Fri, 12 Jun 2026 02:49:34 GMT
• Title: WAM4D: Fast 4D World Action Model via Spatial Register Tokens
• Abstract summary: 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.
• Score: 52.16661403052964
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World action models (WAMs) have recently shown promise in jointly modeling future observations and executable robot actions. However, most existing WAMs still operate in 2D video or latent spaces, where visually plausible rollouts miss the 3D spatial constraints and occluded contact geometry required for precise manipulation. While geometric foundation models offer strong priors for recovering dense 3D structure and motion from visual observations, forcing WAMs to predict the dense 4D representation introduces costly geometric decoding and slows down causal action generation. To address the trade-off, we present WAM4D, a fast 4D world action model that uses lightweight spatial register tokens as training-time future-depth readouts to transfer pretrained geometric priors into a causal video-action transformer, then removes the register branch for lightweight action inference. To prevent non-causal shortcuts, we further design causal mixture attention for the Mixture-of-Transformers (MoT) WAM backbone, defining modality-specific visibility among video, action, and geometry tokens. Comprehensive experiments on RoboTwin 2.0 and challenging real-world manipulation tasks show that WAM4D improves spatial consistency and achieves competitive action prediction while maintaining efficient inference.

Related papers

• GeomVLA: Unifying Scene, Motion, and Action in 3D [19.277341680583834]
  We present GeomVLA, a model that unifies perception, latent scene motion prediction, and action generation within a shared robot-centric 3D coordinate frame.<n>Our approach lifts pretrained VLM features into spatially grounded 3D scene tokens using depth and camera calibration.<n>We introduce a 3D Scene Trajectory Denoiser, a task-conditioned module that learns a latent representation of how scene points are expected to move in 3D.
  arXiv  Detail & Related papers  (2026-09-12T08:51:52Z)
• LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models [64.11117186468533]
  World models enable agents to perform forward rollout and planning without real-world interaction.<n>Most existing LAMs rely on single-view inputs and operate primarily in 2D pixel space.<n>We propose LAWM-3D, which introduces three tightly coupled key designs for learning 3D-aware latent actions.
  arXiv  Detail & Related papers  (2026-08-06T07:47:01Z)
• 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)
• Learning 4D Geometric Priors for Inference-Efficient World Action Models [26.63633606928882]
  World Action Models (WAMs) have shown strong potential for robotic manipulation by jointly modeling visual future dynamics and executable action sequences.<n>We propose MECo-WAM, a Multi-Expert Co-Training World Action Model that injects action-relevant 4D geometric priors into video-action representations.<n>Experiments on LIBERO (98.2%), RoboTwin 2.0 (92.6%), and challenging real-world manipulation tasks show that MECo-WAM improves manipulation performance without increasing inference cost.
  arXiv  Detail & Related papers  (2026-07-06T07:10:22Z)
• StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation [6.0744834626758495]
  StemVLA is a novel framework that explicitly incorporates both future-oriented 3D spatial knowledge and historical 4D representations into action prediction.<n>We show that StemVLA significantly improves long-horizon task success and state-of-the-art performance on the CALVIN ABC-D benchmark [46], achieving an average sequence length of XXX.
  arXiv  Detail & Related papers  (2026-02-27T06:43:37Z)
• 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)
• Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis [53.48281548500864]
  Motion 3-to-4 is a feed-forward framework for synthesising high-quality 4D dynamic objects from a single monocular video.<n>Our model learns a compact motion latent representation and predicts per-frame trajectories to recover complete robustness, temporally coherent geometry.
  arXiv  Detail & Related papers  (2026-01-20T18:59:48Z)
• Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding [54.859943475818234]
  We present Motion4D, a novel framework that integrates 2D priors from foundation models into a unified 4D Gaussian Splatting representation.<n>Our method features a two-part iterative optimization framework: 1) Sequential optimization, which updates motion and semantic fields in consecutive stages to maintain local consistency, and 2) Global optimization, which jointly refines all attributes for long-term coherence.<n>Our method significantly outperforms both 2D foundation models and existing 3D-based approaches across diverse scene understanding tasks, including point-based tracking, video object segmentation, and novel view synthesis.
  arXiv  Detail & Related papers  (2025-12-03T09:32:56Z)
• VLA-4D: Embedding 4D Awareness into Vision-Language-Action Models for SpatioTemporally Coherent Robotic Manipulation [54.81449795163812]
  We develop a general VLA model with 4D awareness for temporally coherent robotic manipulation.<n>We extract visual features, embed 1D time into 3D positions for 4D embeddings, and fuse them into a unified visual representation via a cross-attention mechanism.<n>Within this framework, the designed visual action jointly make robotic manipulation spatially-smooth and temporally temporally coherent.
  arXiv  Detail & Related papers  (2025-11-21T12:26:30Z)
• SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer [57.506654943449796]
  We propose an efficient, sparse-controlled video-to-4D framework named SC4D that decouples motion and appearance. Our method surpasses existing methods in both quality and efficiency. We devise a novel application that seamlessly transfers motion onto a diverse array of 4D entities.
  arXiv  Detail & Related papers  (2024-04-04T18:05:18Z)
• 4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface [7.637832293935966]
  We introduce 4DComplete, a novel data-driven approach that estimates the non-rigid motion for the unobserved geometry. For network training, we constructed a large-scale synthetic dataset called DeformingThings4D.
  arXiv  Detail & Related papers  (2021-05-05T07:39:12Z)

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.