{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/from-grounding-to-manipulation-case-studies","title":"From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems","arxiv_id":"2505.15685","date":"2025-05-21","proceeding":null,"authors":["Xiuchao Sui","Daiying Tian","Qi Sun","Ruirui Chen","Dongkyu Choi","Kenneth Kwok","Soujanya Poria"],"abstract":"Foundation models (FMs) are increasingly used to bridge language and action in embodied agents, yet the operational characteristics of different FM integration strategies remain under-explored -- particularly for complex instruction following and versatile action generation in changing environments. This paper examines three paradigms for building robotic systems: end-to-end vision-language-action (VLA) models that implicitly integrate perception and planning, and modular pipelines incorporating either vision-language models (VLMs) or multimodal large language models (LLMs). We evaluate these paradigms through two focused case studies: a complex instruction grounding task assessing fine-grained instruction understanding and cross-modal disambiguation, and an object manipulation task targeting skill transfer via VLA finetuning. Our experiments in zero-shot and few-shot settings reveal trade-offs in generalization and data efficiency. By exploring performance limits, we distill design implications for developing language-driven physical agents and outline emerging challenges and opportunities for FM-powered robotics in real-world conditions.","url_abs":"https://arxiv.org/abs/2505.15685v1","url_pdf":"https://arxiv.org/pdf/2505.15685v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"from-grounding-to-manipulation-case-studies","repo_url":"https://github.com/hritdy/claw_machine","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"from-grounding-to-manipulation-case-studies","repo_url":"https://github.com/xiuchao/instructiongrounding","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"from-grounding-to-manipulation-case-studies","repo_url":"https://github.com/HRItdy/VLA_Replication","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"pick-screw","name":"pick_screw","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}