StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation

• URL: http://arxiv.org/abs/2602.23721v1
• Date: Fri, 27 Feb 2026 06:43:37 GMT
• Title: StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation
• Authors: Jiasong Xiao, Yutao She, Kai Li, Yuyang Sha, Ziang Cheng, Ziang Tong,
• Abstract summary: 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.
• Score: 6.0744834626758495
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language-action (VLA) models integrate visual observations and language instructions to predict robot actions, demonstrating promising generalization in manipulation tasks. However, most existing approaches primarily rely on direct mappings from 2D visual inputs to action sequences, without explicitly modeling the underlying 3D spatial structure or temporal world dynamics. Such representations may limit spatial reasoning and long-horizon decision-making in dynamic environments. To address this limitation, we propose StemVLA, a novel framework that explicitly incorporates both future-oriented 3D spatial knowledge and historical 4D spatiotemporal representations into action prediction. First, instead of relying solely on observed images, StemVLA forecasts structured 3D future spatial-geometric world knowledge, enabling the model to anticipate upcoming scene geometry and object configurations. Second, to capture temporal consistency and motion dynamics, we feed historical image frames into a pretrained video-geometry transformer backbone to extract implicit 3D world representations, and further aggregate them across time using a temporal attention module, termed VideoFormer [20], forming a unified 4D historical spatiotemporal representation. By jointly modeling 2D observations, predicted 3D future structure, and aggregated 4D temporal dynamics, StemVLA enables more comprehensive world understanding for robot manipulation. Extensive experiments in simulation demonstrate that StemVLA significantly improves long-horizon task success and achieves state-of-the-art performance on the CALVIN ABC-D benchmark [46], achieving an average sequence length of XXX.

Related papers

• RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space [51.441415833480505]
  RAYNOVA is a multiview world model for driving scenarios that employs a dual-causal autoregressive framework.<n>It constructs an isotropic-temporal representation across views, frames, and scales based on relative Plcker-ray positional encoding.
  arXiv  Detail & Related papers  (2026-02-24T08:41:40Z)
• 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)
• 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)
• Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding [11.222744122842023]
  We introduce a plug-and-play module that implicitly incorporates 3D geometry features into Vision-Language-Action (VLA) models.<n>Our method significantly improves the performance of state-of-the-art VLA models across diverse scenarios.
  arXiv  Detail & Related papers  (2025-07-01T04:05:47Z)
• Learning 3D Persistent Embodied World Models [84.40585374179037]
  We introduce a new persistent embodied world model with an explicit memory of previously generated content.<n>During generation time, our video diffusion model predicts RGB-D video of the future observations of the agent.<n>This generation is then aggregated into a persistent 3D map of the environment.
  arXiv  Detail & Related papers  (2025-05-05T17:59:17Z)
• TesserAct: Learning 4D Embodied World Models [66.8519958275311]
  We learn a 4D world model by training on RGB-DN (RGB, Depth, and Normal) videos.<n>This not only surpasses traditional 2D models by incorporating detailed shape, configuration, and temporal changes into their predictions, but also allows us to effectively learn accurate inverse dynamic models for an embodied agent.
  arXiv  Detail & Related papers  (2025-04-29T17:59:30Z)
• 3D-VLA: A 3D Vision-Language-Action Generative World Model [68.0388311799959]
  Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. We propose 3D-VLA by introducing a new family of embodied foundation models that seamlessly link 3D perception, reasoning, and action. Our experiments on held-in datasets demonstrate that 3D-VLA significantly improves the reasoning, multimodal generation, and planning capabilities in embodied environments.
  arXiv  Detail & Related papers  (2024-03-14T17:58:41Z)
• A Graph Attention Spatio-temporal Convolutional Network for 3D Human Pose Estimation in Video [7.647599484103065]
  We improve the learning of constraints in human skeleton by modeling local global spatial information via attention mechanisms. Our approach effectively mitigates depth ambiguity and self-occlusion, generalizes to half upper body estimation, and achieves competitive performance on 2D-to-3D video pose estimation.
  arXiv  Detail & Related papers  (2020-03-11T14:54:40Z)

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.