# MoS-VLA: A Vision-Language-Action Model with One-Shot Skill Adaptation

arXiv: https://arxiv.org/abs/2510.16617 · HTML: https://mlsanity.com/paper/2510.16617/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 18 Oct 2025.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)

## Builds on (most cited first, 24 of 24)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [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)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Differentiable Convex Optimization Layers](https://mlsanity.com/paper/1910.12430/) (2019)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [Learning One Representation to Optimize All Rewards](https://mlsanity.com/paper/2103.07945/) (2021)
- [In-Context Imitation Learning via Next-Token Prediction](https://mlsanity.com/paper/2408.15980/) (2024)
- [Zero-Shot Reinforcement Learning via Function Encoders](https://mlsanity.com/paper/2401.17173/) (2024)
- [Meta Reinforcement Learning with Task Embedding and Shared Policy](https://mlsanity.com/paper/1905.06527/) (2019)
- [Zero-Shot Transfer of Neural ODEs](https://mlsanity.com/paper/2405.08954/) (2024)
- [Function Encoders: A Principled Approach to Transfer Learning in Hilbert Spaces](https://mlsanity.com/paper/2501.18373/) (2025)

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

- [GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization](https://mlsanity.com/paper/2605.12369/) (2026)
- [Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation](https://mlsanity.com/paper/2605.07381/) (2026)
- [UniManip: General-Purpose Zero-Shot Robotic Manipulation with Agentic Operational Graph](https://mlsanity.com/paper/2602.13086/) (2026)
- [Train Together or Merge Later? Unifying VLA Experts via a Shared Action Interface](https://mlsanity.com/paper/2609.33125/) (2026)
- [VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action Models](https://mlsanity.com/paper/2610.06271/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models trained on large robot datasets promise general-purpose, robust control across diverse domains and embodiments. However, existing approaches often fail out-of-the-box when deployed in novel environments, embodiments, or tasks. We introduce Mixture of Skills VLA (MoS-VLA), a framework that represents robot manipulation policies as linear combinations of a finite set of learned basis functions. During pretraining, MoS-VLA jointly learns these basis functions across datasets from the Open X-Embodiment project, producing a structured skill space. At test time, adapting to a new task requires only a single expert demonstration. The corresponding skill representation is then inferred via a lightweight convex optimization problem that minimizes the L1 action error, without requiring gradient updates. This gradient-free adaptation incurs minimal overhead while enabling rapid instantiation of new skills. Empirically, MoS-VLA achieves lower action-prediction error on five out of five unseen datasets and succeeds in both simulation and real-robot tasks where a pretrained VLA model fails outright. Project page: mos-vla.github.io/