# An Empirical Study and Open Testbed for Federated Fine-Tuning of Vision-Language-Action Models arXiv: https://arxiv.org/abs/2609.22973 · HTML: https://mlsanity.com/paper/2609.22973/ ## Key facts - No citing papers in the map yet (data through 14 Oct 2026). - Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models. - Builds on 33 of its 38 references that are in the map. - First posted on arXiv 19 Sep 2026. ## 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, 30 of 33) - [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021) - [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016) - [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023) - [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018) - [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) - [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025) - [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023) - [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022) - [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025) - [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020) - [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024) - [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020) - [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020) - [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021) - [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019) - [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025) - [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020) - [LoRA Learns Less and Forgets Less](https://mlsanity.com/paper/2405.09673/) (2024) - [LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization](https://mlsanity.com/paper/2510.03827/) (2025) - [Diverse Weight Averaging for Out-of-Distribution Generalization](https://mlsanity.com/paper/2205.09739/) (2022) - [π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities](https://mlsanity.com/paper/2604.15483/) (2026) - [OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning](https://mlsanity.com/paper/2402.06954/) (2024) - [NVIDIA FLARE: Federated Learning from Simulation to Real-World](https://mlsanity.com/paper/2210.13291/) (2022) - [Selective Aggregation for Low-Rank Adaptation in Federated Learning](https://mlsanity.com/paper/2410.01463/) (2024) - [Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems](https://mlsanity.com/paper/1901.06455/) (2019) - [On the Importance and Applicability of Pre-Training for Federated Learning](https://mlsanity.com/paper/2206.11488/) (2022) - [Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning](https://mlsanity.com/paper/2210.08090/) (2022) - [RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies](https://mlsanity.com/paper/2604.09860/) (2026) - [FedVLA: Federated Vision-Language-Action Learning with Dual Gating Mixture-of-Experts for Robotic Manipulation](https://mlsanity.com/paper/2508.02190/) (2025) ## Abstract (arXiv) Adapting a pretrained Vision-Language-Action (VLA) model to a new robot, environment, or task requires demonstrations that are collected locally and often discarded. Federated learning is a promising approach to exploiting such distributed demonstrations by learning a shared policy. However, whether it can adapt large pretrained VLAs remains an open question, and a lack of reproducible benchmarks for pretrained VLAs and reusable training frameworks makes existing results difficult to compare. In this paper, we conduct a systematic study of federated fine-tuning of three modern pretrained VLA policies on the 40 simulated tasks of the LIBERO manipulation benchmark, and on six real-world tasks in two real-robot experiments, with demonstrations collected across two and three sites, respectively. Our study analyzes the key choices in this setting, spanning multiple federated parameter scopes, three aggregation algorithms, and evaluation under distribution shift. Based on the study, we derive a series of lessons, including the dominance of the federated scope over the choice of aggregation algorithm and the difficulty of matching centralized fine-tuning on physical robots, where cross-site heterogeneity is stronger than simulation captures. We also highlight opportunities for federated VLA learning, such as the ability to match centralized fine-tuning on heterogeneous data, to remain at least as robust as centralized fine-tuning under distribution shift, and to personalize, with each client federating part of the policy and keeping the rest local, which helps where the policy's pretraining is weak but leaves no usable global model. We open-source decentvla, the model- and runtime-agnostic testbed behind the study, to facilitate future research and fair comparisons in federated VLA learning.