# From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings

arXiv: https://arxiv.org/abs/2511.21428 · HTML: https://mlsanity.com/paper/2511.21428/

## Key facts

- Cited by 1 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 23 of its 33 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## 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, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (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)
- [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)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [Magma: A Foundation Model for Multimodal AI Agents](https://mlsanity.com/paper/2502.13130/) (2025)
- [Learning to Act without Actions](https://mlsanity.com/paper/2312.10812/) (2023)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos](https://mlsanity.com/paper/2412.04445/) (2024)
- [AMPLIFY: Actionless Motion Priors for Robot Learning from Videos](https://mlsanity.com/paper/2506.14198/) (2025)
- [Algorithmic Capabilities of Random Transformers](https://mlsanity.com/paper/2410.04368/) (2024)
- [Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling](https://mlsanity.com/paper/2210.05043/) (2022)
- [Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment](https://mlsanity.com/paper/2403.19225/) (2024)
- [OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation](https://mlsanity.com/paper/2309.06276/) (2023)
- [Efficient Temporal Action Segmentation via Boundary-aware Query Voting](https://mlsanity.com/paper/2405.15995/) (2024)

## Built on by (most cited first, 1 of 1)

- [Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA](https://mlsanity.com/paper/2610.05025/) (2026)

## Abstract (arXiv)

We present a novel unsupervised framework to unlock vast unlabeled human demonstration data from continuous industrial video streams for Vision-Language-Action (VLA) model pre-training. Our method first trains a lightweight motion tokenizer to encode motion dynamics, then employs an unsupervised action segmenter leveraging a novel "Latent Action Energy" metric to discover and segment semantically coherent action primitives. The pipeline outputs both segmented video clips and their corresponding latent action sequences, providing structured data directly suitable for VLA pre-training. Evaluations on public benchmarks and a proprietary electric motor assembly dataset demonstrate effective segmentation of key tasks performed by humans at workstations. Further clustering and quantitative assessment via a Vision-Language Model confirm the semantic coherence of the discovered action primitives. To our knowledge, this is the first fully automated end-to-end system for extracting and organizing VLA pre-training data from unstructured industrial videos, offering a scalable solution for embodied AI integration in manufacturing.