@inproceedings{sui-etal-2025-grounding,
title = "From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems",
author = "Sui, Xiuchao and
Tian, Daiying and
Sun, Qi and
Chen, Ruirui and
Choi, Dongkyu and
Kwok, Kenneth and
Poria, Soujanya",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.69/",
doi = "10.18653/v1/2025.findings-emnlp.69",
pages = "1324--1340",
ISBN = "979-8-89176-335-7",
abstract = "Foundation models (FMs) are increasingly applied to bridge language and action in embodied agents, yet the operational characteristics of different integration strategies remain under-explored{---}especially for complex instruction following and versatile action generation in changing environments. We investigate three paradigms for robotic systems: end-to-end vision-language-action models (VLAs) that implicitly unify perception and planning, and modular pipelines using either vision-language models (VLMs) or multimodal large language models (MLLMs). Two case studies frame the comparison: instruction grounding, which probs fine-grained language understanding and cross-modal disambiguation; and object manipulation, which targets skill transfer via VLA finetuning. Our experiments reveal trade-offs in system scale, generalization and data efficiency. These findings indicate design lessons for language-driven physical agents and point to challenges and opportunities for FM-powered robotics in real-world conditions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sui-etal-2025-grounding">
<titleInfo>
<title>From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiuchao</namePart>
<namePart type="family">Sui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daiying</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruirui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongkyu</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Kwok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Foundation models (FMs) are increasingly applied to bridge language and action in embodied agents, yet the operational characteristics of different integration strategies remain under-explored—especially for complex instruction following and versatile action generation in changing environments. We investigate three paradigms for robotic systems: end-to-end vision-language-action models (VLAs) that implicitly unify perception and planning, and modular pipelines using either vision-language models (VLMs) or multimodal large language models (MLLMs). Two case studies frame the comparison: instruction grounding, which probs fine-grained language understanding and cross-modal disambiguation; and object manipulation, which targets skill transfer via VLA finetuning. Our experiments reveal trade-offs in system scale, generalization and data efficiency. These findings indicate design lessons for language-driven physical agents and point to challenges and opportunities for FM-powered robotics in real-world conditions.</abstract>
<identifier type="citekey">sui-etal-2025-grounding</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.69</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.69/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1324</start>
<end>1340</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems
%A Sui, Xiuchao
%A Tian, Daiying
%A Sun, Qi
%A Chen, Ruirui
%A Choi, Dongkyu
%A Kwok, Kenneth
%A Poria, Soujanya
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F sui-etal-2025-grounding
%X Foundation models (FMs) are increasingly applied to bridge language and action in embodied agents, yet the operational characteristics of different integration strategies remain under-explored—especially for complex instruction following and versatile action generation in changing environments. We investigate three paradigms for robotic systems: end-to-end vision-language-action models (VLAs) that implicitly unify perception and planning, and modular pipelines using either vision-language models (VLMs) or multimodal large language models (MLLMs). Two case studies frame the comparison: instruction grounding, which probs fine-grained language understanding and cross-modal disambiguation; and object manipulation, which targets skill transfer via VLA finetuning. Our experiments reveal trade-offs in system scale, generalization and data efficiency. These findings indicate design lessons for language-driven physical agents and point to challenges and opportunities for FM-powered robotics in real-world conditions.
%R 10.18653/v1/2025.findings-emnlp.69
%U https://aclanthology.org/2025.findings-emnlp.69/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.69
%P 1324-1340
Markdown (Informal)
[From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems](https://aclanthology.org/2025.findings-emnlp.69/) (Sui et al., Findings 2025)
ACL