# Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action Policies

arXiv: https://arxiv.org/abs/2608.03727 · HTML: https://mlsanity.com/paper/2608.03727/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in 3D and spatial-aware VLA, one of 13 directions in Vision-language-action models.
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- Vision-language-action models / [3D and spatial-aware VLA](https://mlsanity.com/vla/3d-and-spatial-aware-vla/)

## Builds on (most cited first, 28 of 28)

- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs](https://mlsanity.com/paper/2512.15692/) (2025)
- [Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model](https://mlsanity.com/paper/2510.12276/) (2025)
- [Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation](https://mlsanity.com/paper/2405.01527/) (2024)
- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026)
- [F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions](https://mlsanity.com/paper/2509.06951/) (2025)
- [3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model](https://mlsanity.com/paper/2506.06199/) (2025)
- [World Guidance: World Modeling in Condition Space for Action Generation](https://mlsanity.com/paper/2602.22010/) (2026)
- [GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulation](https://mlsanity.com/paper/2512.16811/) (2025)
- [TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos](https://mlsanity.com/paper/2511.21690/) (2025)
- [Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels](https://mlsanity.com/paper/2603.02573/) (2026)
- [LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior](https://mlsanity.com/paper/2603.25399/) (2026)
- [Point Tracking Improves World Action Models](https://mlsanity.com/paper/2605.23856/) (2026)

## Built on by (most cited first, 5 of 5)

- [InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data](https://mlsanity.com/paper/2609.31394/) (2026)
- [FOCAL-VLA: Subtask-Guided Geometry Distillation and Implicit World Modeling for Vision-Language-Action Models](https://mlsanity.com/paper/2609.21228/) (2026)
- [MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation](https://mlsanity.com/paper/2609.21474/) (2026)
- [JAMB: Joint Action-Motion Diffusion for Bimanual Manipulation](https://mlsanity.com/paper/2609.25322/) (2026)
- [CoRe-WAM: Correspondence-Aligned Temporal Residuals for World Action Models](https://mlsanity.com/paper/2609.27314/) (2026)

## Abstract (arXiv)

Action labels tell a vision-language-action (VLA) policy which robot commands to imitate, but not how those commands change the 3D world. The aligned demonstration clip contains this missing supervision because its K frame transitions record the geometry, motion, visibility, and camera change produced during the corresponding K actions. We introduce Track4Action, a framework that distills this realized transition from a frozen world-centric 3D tracker into a current-observation VLA policy. During training, Track4World encodes the clip Vt:t+K into a pooled tracker feature. Learnable track queries infer this feature from current VLA hidden states, match it in a shared space, and condition a flow-matching action head through a feature-wise gate. The tracker feature only defines the alignment target, so neither the clip nor the tracker is used at deployment. Track4Action reaches 82.3% on zero-shot LIBERO-Plus, improving the alignment-free variant by 7.6 points and LaMP by 3.0 points. It obtains 80.44% and 81.48% on the clean and randomized RoboTwin 2.0 splits, and 67.5% average success across four physical bimanual tasks, 25.0 points above the alignment-free variant. The gains across simulation and physical tasks support action-aligned 3D tracker features as privileged supervision for tracker-free VLA deployment. Our project page is available at https://wing0night.github.io/track4action-project-page.