FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Reuss, Moritz, Zhou, Hongyi, Rühle, Marcel, Yağmurlu, Ömer Erdinç, Otto, Fabian, Lioutikov, Rudolf
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914023969128448
author Reuss, Moritz
Zhou, Hongyi
Rühle, Marcel
Yağmurlu, Ömer Erdinç
Otto, Fabian
Lioutikov, Rudolf
author_facet Reuss, Moritz
Zhou, Hongyi
Rühle, Marcel
Yağmurlu, Ömer Erdinç
Otto, Fabian
Lioutikov, Rudolf
contents Developing efficient Vision-Language-Action (VLA) policies is crucial for practical robotics deployment, yet current approaches face prohibitive computational costs and resource requirements. Existing diffusion-based VLA policies require multi-billion-parameter models and massive datasets to achieve strong performance. We tackle this efficiency challenge with two contributions: intermediate-modality fusion, which reallocates capacity to the diffusion head by pruning up to $50\%$ of LLM layers, and action-specific Global-AdaLN conditioning, which cuts parameters by $20\%$ through modular adaptation. We integrate these advances into a novel 950 M-parameter VLA called FLOWER. Pretrained in just 200 H100 GPU hours, FLOWER delivers competitive performance with bigger VLAs across $190$ tasks spanning ten simulation and real-world benchmarks and demonstrates robustness across diverse robotic embodiments. In addition, FLOWER achieves a new SoTA of 4.53 on the CALVIN ABC benchmark. Demos, code and pretrained weights are available at https://intuitive-robots.github.io/flower_vla/.
format Preprint
id arxiv_https___arxiv_org_abs_2509_04996
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies
Reuss, Moritz
Zhou, Hongyi
Rühle, Marcel
Yağmurlu, Ömer Erdinç
Otto, Fabian
Lioutikov, Rudolf
Robotics
Developing efficient Vision-Language-Action (VLA) policies is crucial for practical robotics deployment, yet current approaches face prohibitive computational costs and resource requirements. Existing diffusion-based VLA policies require multi-billion-parameter models and massive datasets to achieve strong performance. We tackle this efficiency challenge with two contributions: intermediate-modality fusion, which reallocates capacity to the diffusion head by pruning up to $50\%$ of LLM layers, and action-specific Global-AdaLN conditioning, which cuts parameters by $20\%$ through modular adaptation. We integrate these advances into a novel 950 M-parameter VLA called FLOWER. Pretrained in just 200 H100 GPU hours, FLOWER delivers competitive performance with bigger VLAs across $190$ tasks spanning ten simulation and real-world benchmarks and demonstrates robustness across diverse robotic embodiments. In addition, FLOWER achieves a new SoTA of 4.53 on the CALVIN ABC benchmark. Demos, code and pretrained weights are available at https://intuitive-robots.github.io/flower_vla/.
title FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies
topic Robotics
url https://arxiv.org/abs/2509.04996