Are Foundation Models the Route to Full-Stack Transfer in Robotics?

Freek Stulp; Samuel Bustamante; João Silvério; Alin Albu-Schäffer; Jeannette Bohg; Shuran Song

cs.ROFeb 25, 2026

Are Foundation Models the Route to Full-Stack Transfer in Robotics?

Authors: Freek Stulp, Samuel Bustamante, João Silvério, Alin Albu-Schäffer, Jeannette Bohg, Shuran Song

Organizations: Institute of Robotics and Mechatronics, German Aerospace Center (DLR), Wessling, Germany. · Stanford AI Lab, Stanford University, Palo Alto, USA.

Abstract

In humans and robots alike, transfer learning occurs at different levels of abstraction, from high-level linguistic transfer to low-level transfer of motor skills. In this article, we provide an overview of the impact that foundation models and transformer networks have had on these different levels, bringing robots closer than ever to "full-stack transfer". Considering LLMs, VLMs and VLAs from a robotic transfer learning perspective allows us to highlight recurring concepts for transfer, beyond specific implementations. We also consider the challenges of data collection and transfer benchmarks for robotics in the age of foundation models. Are foundation models the route to full-stack transfer in robotics? Our expectation is that they will certainly stay on this route as a key technology.

Figures & tables

Figure 2: Transformer networks have had a profound impact on the performance of LLMs/VLMs ( Section 2 ) and the ability to learn visuomotor policies, e.g. diffusion policies, from demonstrations ( Section 3 ). VLAs ( Section 4 ) arose as extensions of VLMs. Denoising-based VLAs ( Section 4.3 ) arose by merging diffusion policies or flow matching with VLMs, which was made possible by the shared modality of vision.

Transfer Learning “leverages prior knowledge from a source space, composed by a robot, a task, and an environment, to improve the performance in a target space, where one or more modes differs from the source space.” [ 1 ]

Foundation models are “trained on broad data (generally using self-supervision at scale) that can be adapted to a wide range of downstream tasks.” [ 8 ] . This definition applies to all LLMs, VLMs and VLAs cited in this paper.

A Vision Language Action model (VLA) “is a system that takes visual observations and natural language instructions as required inputs and may incorporate additional sensory modalities. It produces robot actions by directly generating control commands.” [ 2 ] . In Section 4 , we adhere to the classification of VLA architectures in Fig. 4 in [ 2 ] .

Table 1: Definitions used in this article.

Figure 3: Exemplary implementations for three distinct classes of VLAs, according to the classification in [ 2 ] :

\bullet

OpenVLA [ 17 ] , see Section 4.1 ;

\bullet

\pi_{0}

-FAST [ 29 ] , see Section 4.2 ;

\bullet

\pi_{0}

[ 5 ] , see Section 4.3 . The order follows the structure of the article, and is not chronological.

Figure 4: Overview knowledge insulation implementations in

\pi_{0.5}

[ 16 ] ,

\pi_{0.5}

-KI [ 27 ] , and

\pi_{0.6}

[ 32 ] , which are implementations of denoising-based VLAs. Whereas Figure 3 showed

\pi_{0}

and

\pi_{0}

-FAST and focussed on inference, this figure rather depicts different training phases.

Transfer Learning

Transfer learning studies how models reuse knowledge across tasks, domains, or modalities when target data or computation are limited.

See all 420 papers

Foundation Models in Robotics: A Comprehensive Review of Methods, Models, Datasets, Challenges and Future Research Directions
Apr 16, 2026Aggelos Psiris, Vasileios Argyriou, Evangelos K. Markakis +4Large Language Model-Based Robot Planning Robot Foundation Models
Department of Informatics and Telematics, Harokopio University of Athens, Athens, Greece · Department of Networks and Digital Media, Kingston University, London, United Kingdom · Department of Electrical and Computer Engineering, Hellenic Mediterranean University, Heraklion, Greece +4
ARC: A Reasoning Recipe for Robot Foundation Models
Oct 8, 2026Gokul Puthumanaillam, Tao Sun, Elie Aljalbout +5Robot Foundation Models Reasoning for VLA Models
University of Illinois Urbana-Champaign · NVIDIA · Stanford University +2
The Embodiment Gap in Robot Foundation Models
Aug 19, 2026Yukiyasu Domae, Keisuke Shirai, Hanbit Oh +7Robotics Robot Foundation Models
National Institute of Advanced Industrial Science and Technology (AIST), Japan

Apr 16, 2026J/K move · Enter open · S save

Foundation Models in Robotics: A Comprehensive Review of Methods, Models, Datasets, Challenges and Future Research Directions

Aggelos Psiris, Vasileios Argyriou, Evangelos K. Markakis, Panagiotis Sarigiannidis+3

Department of Informatics and Telematics, Harokopio University of Athens, Athens, Greece · Department of Networks and Digital Media, Kingston University, London, United Kingdom · Department of Electrical and Computer Engineering, Hellenic Mediterranean University, Heraklion, Greece+4

Large Language Model-Based Robot Planning Robot Foundation Models Cross-Embodiment Robot Learning Vision-Language-Action Models Multimodal Foundation Models VLMs for Robotics

Open paper AskPDF arXiv

Over the recent years, the field of robotics has been undergoing a transformative paradigm shift from fixed, single-task, domain-specific solutions towards adaptive, multi-function, general-purpose agents, capable of operating in complex, open-world, and dynamic environments. This tremendous advancement is primarily driven by the emergence of Foundation Models (FMs), i.e., large-scale neural-network architectures trained on massive, heterogeneous datasets that provide unprecedented capabilities in multi-modal understanding and reasoning, long-horizon planning, and cross-embodiment generalization. In this context, the current study provides a holistic, systematic, and in-depth review of the research landscape of FMs in robotics. In particular, the evolution of the field is initially delineated through five distinct research phases, spanning from the early incorporation of Natural Language Processing (NLP) and Computer Vision (CV) models to the current frontier of multi-sensory generalization and real-world deployment. Subsequently, a highly-granular taxonomic investigation of the literature is performed, examining the following key aspects: a) the employed FM types, including LLMs, VFMs, VLMs, and VLAs, b) the underlying neural-network architectures, c) the adopted learning paradigms, d) the different learning stages of knowledge incorporation, e) the major robotic tasks, and f) the main real-world application domains. For each aspect, comparative analysis and critical insights are provided. Moreover, a report on the publicly available datasets used for model training and evaluation across the considered robotic tasks is included. Furthermore, a hierarchical discussion on the current open challenges and promising future research directions in the field is incorporated.

Abstract

Transfer Learning

Explore similar work

Foundation Models in Robotics: A Comprehensive Review of Methods, Models, Datasets, Challenges and Future Research Directions

ARC: A Reasoning Recipe for Robot Foundation Models

The Embodiment Gap in Robot Foundation Models