mlsanityData to 7 Oct 2026

Spatial Traces: Enhancing VLA Models with Spatial-Temporal Understanding

arXiv 2508.09032 ↗First posted 12 Aug 2025cs.CV cs.AI cs.ROcited by 11

On the map: Vision-language-action models → 3D and spatial-aware VLA

Abstract (arXiv)

Vision-Language-Action models have demonstrated remarkable capabilities in predicting agent movements within virtual environments and real-world scenarios based on visual observations and textual instructions. Although recent research has focused on enhancing spatial and temporal understanding independently, this paper presents a novel approach that integrates both aspects through visual prompting. We introduce a method that projects visual traces of key points from observations onto depth maps, enabling models to capture both spatial and temporal information simultaneously. The experiments in SimplerEnv show that the mean number of tasks successfully solved increased for 4% compared to SpatialVLA and 19% compared to TraceVLA. Furthermore, we show that this enhancement can be achieved with minimal training data, making it particularly valuable for real-world applications where data collection is challenging. The project page is available at https://ampiromax.github.io/ST-VLA.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Placed in 3D and spatial-aware VLA, one of 13 directions in Vision-language-action models. Builds on 27 of its 37 references that are in the map. First posted on arXiv 12 Aug 2025.

Builds on

27 of 37 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model27 Jan
  2. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies13 Dec

Other references · 25

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  3. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  5. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  6. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  7. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  8. 2023CoTracker: It is Better to Track Togethercited by 516
  9. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  10. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  11. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 459
  12. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
13 more
  1. 2022VIMA: General Robot Manipulation with Multimodal Promptscited by 403
  2. 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystackcited by 211
  3. 2024PaliGemma 2: A Family of Versatile VLMs for Transfercited by 204
  4. 2023Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planningcited by 161
  5. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 138
  6. 2023RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketchescited by 131
  7. 2023RoboVQA: Multimodal Long-Horizon Reasoning for Roboticscited by 116
  8. 2023RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitationcited by 88
  9. 2024What Matters in Building Vision-Language-Action Models for Generalist Robotscited by 88
  10. 2024RT-Affordance: Affordances are Versatile Intermediate Representations for Robot Manipulationcited by 40
  11. 2025VerifyLLM: LLM-Based Pre-Execution Task Plan Verification for Robotscited by 14
  12. 2025SEM: Enhancing Spatial Understanding for Robust Robot Manipulationcited by 8
  13. 2025LERa: Replanning with Visual Feedback in Instruction Followingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 8.

11 papers.

  1. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  2. 2026Towards Generalizable Robotic Manipulation in Dynamic Environmentscited by 17
  3. 2026LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Priorcited by 11
  4. 2025OmniVLA: Physically-Grounded Multimodal VLA with Unified Multi-Sensor Perception for Robotic Manipulationcited by 7
  5. 2026μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA Modelscited by 7
  6. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challengescited by 4
  7. 2026UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Modelscited by 3
  8. 2026Robots Need More than VLA and World Modelscited by 2
  9. 2026MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulationcited by 1
  10. 2026AnchorVLA4D: an Anchor-Based Spatial-Temporal Vision-Language-Action Model for Robotic Manipulationcited by 0
  11. 2026Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning
  2. 2026VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing
  3. 2025Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
  4. 2024ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting
  5. 20243D-VLA: A 3D Vision-Language-Action Generative World Model
  6. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
  7. 2025TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
  8. 2025GeoVLA: Empowering 3D Representations in Vision-Language-Action Models