# Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy

arXiv: https://arxiv.org/abs/2609.07470 · HTML: https://mlsanity.com/paper/2609.07470/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models.
- Builds on 30 of its 32 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Placed in

- Vision-language-action models / [Generalist VLA models and benchmarks](https://mlsanity.com/vla/generalist-vla-models-and-benchmarks/)

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

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [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)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [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)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering](https://mlsanity.com/paper/1712.00377/) (2017)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [Language Conditioned Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2005.07648/) (2020)
- [DreamGen: Unlocking Generalization in Robot Learning through Video World Models](https://mlsanity.com/paper/2505.12705/) (2025)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better](https://mlsanity.com/paper/2505.23705/) (2025)
- [Translation Artifacts in Cross-lingual Transfer Learning](https://mlsanity.com/paper/2004.04721/) (2020)
- [Multilingual Instruction Tuning With Just a Pinch of Multilinguality](https://mlsanity.com/paper/2401.01854/) (2024)
- [Shifting the Baseline: Single Modality Performance on Visual Navigation & QA](https://mlsanity.com/paper/1811.00613/) (2018)

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

- [Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models](https://mlsanity.com/paper/2610.10526/) (2026)

## Abstract (arXiv)

Robot foundation models are trained and evaluated predominantly in English, and robot demonstration corpora do not exist for most languages. We study the addition of Greek to an open vision-language-action stack using only machine-rephrased instructions and no architecture changes. The main challenge is measurement rather than translation. Several plausible instruments produce false conclusions: a color-histogram metric rewards noise, a single-goal benchmark scores 84.6% under correct Greek and 82.6% under deliberately wrong instructions, training loss fails to predict Greek success, and single-run comparisons are dominated by seed variation. On a discriminative ninety-task suite with three seeds per arm, a multilingual text tower without Greek demonstrations remains at its wrong-instruction floor, while Greek-only training exceeds its control by at most 2.7 points. Bilingual training yields a consistent 6.7-7.1 point margin over its control and reaches about two fifths of English performance. The policy also overfits the translator's phrasing; training on seven phrasings per task approximately halves this penalty. Warm-starting from a language-adapted world model and unfreezing the text tower both degrade performance. The results support two practical requirements for low-resource robot-policy localization: build a guaranteed null before trusting a metric, and replicate low-resource-language results across seeds.