ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation

• URL: http://arxiv.org/abs/2603.13788v1
• Date: Sat, 14 Mar 2026 06:36:48 GMT
• Title: ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation
• Abstract summary: We propose a unified 3D-4D representation using a unified 3D-4D representation to bridge perception and action.<n>We introduce STHuman, a large-scale human manipulation dataset with 14 and 300k episodes, annotated 2D, 3D, and 4D contexts.<n>Experiments on RLBench and real-world manipulation tasks show that method significantly outperforms state-of-theart baselines.
• Score: 33.92613503473177
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robotic manipulation in open-world environments requires reasoning across semantics, geometry, and long-horizon action dynamics. Existing hierarchical Vision-Language-Action (VLA) frameworks typically use 2D representations to connect high-level reasoning with low-level control, but lack depth awareness and temporal consistency, limiting robustness in complex 3D scenes. We propose ST-VLA, a hierarchical VLA framework using a unified 3D-4D representation to bridge perception and action. ST-VLA converts 2D guidance into 3D trajectories and generates smooth spatial masks that capture 4D spatio-temporal context, providing a stable interface between semantic reasoning and continuous control. To enable effective learning of such representations, we introduce ST-Human, a large-scale human manipulation dataset with 14 tasks and 300k episodes, annotated with 2D, 3D, and 4D supervision via a semi-automated pipeline. Using ST-Human, we train ST-VLM, a spatio-temporal vision-language model that generates spatially grounded and temporally coherent 3D representations to guide policy execution. The smooth spatial masks focus on task-relevant geometry and stabilize latent representations, enabling online replanning and long-horizon reasoning. Experiments on RLBench and real-world manipulation tasks show that \method significantly outperforms state-of-the-art baselines, improving zero-shot success rates by 44.6% and 30.3%. These results demonstrate that offloading spatio-temporal reasoning to VLMs with unified 3D-4D representations substantially improves robustness and generalization for open-world robotic manipulation. Project website: https://oucx117.github.io/ST-VLA/.

Related papers

• VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulation [7.753769810587787]
  Vision-Language-Action (VLA) models have emerged as a powerful end-to-end paradigm for robotic manipulation by mapping language instructions and 2D visual inputs directly to actions.<n>These models lack an explicit, scene-level 3D representation, limiting their ability to reason over spatial layouts and geometric constraints.<n>We present VistaVLA, a novel framework that constructs a geometry- and semantics-aware 3D cognitive representation from 3D Gaussian primitives.
  arXiv  Detail & Related papers  (2026-07-14T05:08:50Z)
• 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)
• 3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance [46.721682793921815]
  3D HAMSTER is a hierarchical framework that closes the gap between state-of-the-art low-level policies and metrically reliable 3D trajectories.<n>Across 3D trajectory prediction, simulation, and real-world manipulation, 3D HAMSTER consistently outperforms proprietary VLMs and 2D-guided baselines.
  arXiv  Detail & Related papers  (2026-06-30T08:31:35Z)
• PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction [57.63073414949329]
  We propose PointACT, a dual-system 3D-aware VLA policy that integrates hierarchical 3D point cloud representations directly into the action decoding process.<n>PointACT employs a multi-scale point-action interaction mechanism with efficient bottleneck window self-attention, enabling evolving action tokens to densely attend to both local geometric detail and global scene structure.
  arXiv  Detail & Related papers  (2026-05-20T17:10:31Z)
• VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models [55.12929235609365]
  Visual backbones of current vision-language-action (VLA) models are predominantly pretrained on 2D image data without explicit 3D geometric supervision.<n>Existing implicit grounding methods partially address this by aligning VLA features with those of 3D-aware foundation models.<n>We propose VEGA, a framework that directly aligns the output of the VLA's visual encoder with spatially-aware features from DINOv2-FiT3D.
  arXiv  Detail & Related papers  (2026-05-11T12:44:26Z)
• GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes [47.88691731631585]
  GMT is a multimodal transformer framework that generates realistic and goal-directed object trajectories.<n>Experiments on synthetic and real-world benchmarks demonstrate that GMT outperforms state-of-the-art human motion and human-object interaction baselines.
  arXiv  Detail & Related papers  (2026-03-18T17:54:35Z)
• MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence [50.11889361459544]
  Humans are born with vision-based 4D spatial-temporal intelligence.<n>Despite its importance, this capability remains a significant bottleneck for current large language models (MLLMs)
  arXiv  Detail & Related papers  (2026-02-28T07:23:36Z)
• 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)
• D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation [66.7166217399105]
  Embodied agents face a critical dilemma that end-to-end models lack interpretability and explicit 3D reasoning.<n>Our model introduces two key innovations: 1) A Dynamic 3D Chain-of-Thought (3D CoT) that unifies planning, grounding, navigation, and question answering within a single 3D-VLM and CoT pipeline; 2) A Synergistic Learning from Fragmented Supervision (SLFS) strategy, which uses a masked autoregressive loss to learn from massive and partially-annotated hybrid data.
  arXiv  Detail & Related papers  (2025-12-14T09:53:15Z)
• 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)
• Abstract 3D Perception for Spatial Intelligence in Vision-Language Models [100.13033631690114]
  Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding.<n>We introduce SandboxVLM, a framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM.<n>Our approach consistently improves spatial intelligence, achieving an 8.3% gain on SAT Real compared with baseline methods.
  arXiv  Detail & Related papers  (2025-11-14T04:16:09Z)
• SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation [63.48859753472547]
  SpatialActor is a framework for robust robotic manipulation that explicitly decouples semantics and geometry.<n>It achieves state-of-the-art performance with 87.4% on RLBench and improves by 13.9% to 19.4% under varying noisy conditions.
  arXiv  Detail & Related papers  (2025-11-12T18:59:08Z)
• GaussRender: Learning 3D Occupancy with Gaussian Rendering [86.89653628311565]
  GaussRender is a module that improves 3D occupancy learning by enforcing projective consistency.<n>Our method penalizes 3D configurations that produce inconsistent 2D projections, thereby enforcing a more coherent 3D structure.
  arXiv  Detail & Related papers  (2025-02-07T16:07:51Z)
• Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation [30.744137117668643]
  Lift3D is a framework that enhances 2D foundation models with implicit and explicit 3D robotic representations to construct a robust 3D manipulation policy.<n>In experiments, Lift3D consistently outperforms previous state-of-the-art methods across several simulation benchmarks and real-world scenarios.
  arXiv  Detail & Related papers  (2024-11-27T18:59:52Z)

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.