# From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2605.04678 · HTML: https://mlsanity.com/paper/2605.04678/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Human-video and latent-action pretraining, one of 13 directions in Vision-language-action models.
- Builds on 35 of its 38 references that are in the map.
- First posted on arXiv 6 May 2026.

## Placed in

- Vision-language-action models / [Human-video and latent-action pretraining](https://mlsanity.com/vla/human-video-and-latent-action-pretraining/)

## Builds on (most cited first, 30 of 35)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [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)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [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)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [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)
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [Behavior Generation with Latent Actions](https://mlsanity.com/paper/2403.03181/) (2024)
- [ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning](https://mlsanity.com/paper/2507.16815/) (2025)
- [VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model](https://mlsanity.com/paper/2509.09372/) (2025)
- [Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model](https://mlsanity.com/paper/2510.12276/) (2025)
- [Learning to Act without Actions](https://mlsanity.com/paper/2312.10812/) (2023)
- [IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI](https://mlsanity.com/paper/2411.00785/) (2024)
- [Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos](https://mlsanity.com/paper/2412.04445/) (2024)
- [villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models](https://mlsanity.com/paper/2507.23682/) (2025)
- [QueST: Self-Supervised Skill Abstractions for Learning Continuous Control](https://mlsanity.com/paper/2407.15840/) (2024)
- [Latent Action Learning Requires Supervision in the Presence of Distractors](https://mlsanity.com/paper/2502.00379/) (2025)
- [Emergence of Human to Robot Transfer in Vision-Language-Action Models](https://mlsanity.com/paper/2512.22414/) (2025)

## Built on by (most cited first, 4 of 4)

- [What Matters for Latent Actions in Robot Learning](https://mlsanity.com/paper/2608.19613/) (2026)
- [How Should Vision-Language-Action Models Use Proprioceptive State?](https://mlsanity.com/paper/2608.03052/) (2026)
- [Native Action-Prior Learning from Videos for World Action Models](https://mlsanity.com/paper/2610.03391/) (2026)
- [What Matters for World Modeling in Vision-Language-Action Models?](https://mlsanity.com/paper/2610.19825/) (2026)

## Abstract (arXiv)

Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous datasets. However, approaches to supervising VLAs with latent actions are fragmented and lack a systematic comparison. This work structures the study of latent action supervision from two perspectives: (i) regularizing the trajectory via image-based latent actions, and (ii) unifying the target space with action-based latent actions. Under a unified VLA baseline, we instantiate and compare four representative integration strategies. Our results reveal a formulation-task correspondence: image-based latent actions benefit long-horizon reasoning and scene-level generalization, whereas action-based latent actions excel at complex motor coordination. Furthermore, we find that directly supervising the VLM with discrete latent action tokens yields the most effective performance. Finally, our experiments offer initial insights into the benefits of latent action supervision in mixed-data, suggesting a promising direction for VLA training. Code is available at https://github.com/RUCKBReasoning/From_Pixels_to_Tokens.