Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Haochen, Pei, Jiahuan, Aliannejadi, Mohammad, Sun, Xin, Ahsan, Moonisa, Yu, Chuang, Ren, Zhaochun, Cesar, Pablo, Wang, Junxiao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.05515
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918102456860672
author Huang, Haochen
Pei, Jiahuan
Aliannejadi, Mohammad
Sun, Xin
Ahsan, Moonisa
Yu, Chuang
Ren, Zhaochun
Cesar, Pablo
Wang, Junxiao
author_facet Huang, Haochen
Pei, Jiahuan
Aliannejadi, Mohammad
Sun, Xin
Ahsan, Moonisa
Yu, Chuang
Ren, Zhaochun
Cesar, Pablo
Wang, Junxiao
contents Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grained spatial reasoning and precise object state detection are required. In this work, we explore LEGO Co-builder, a hybrid benchmark combining real-world LEGO assembly logic with programmatically generated multimodal scenes. The dataset captures stepwise visual states and procedural instructions, allowing controlled evaluation of instruction-following, object detection, and state detection. We introduce a unified framework and assess leading VLMs such as GPT-4o, Gemini, and Qwen-VL, under zero-shot and fine-tuned settings. Our results reveal that even advanced models like GPT-4o struggle with fine-grained assembly tasks, with a maximum F1 score of just 40.54\% on state detection, highlighting gaps in fine-grained visual understanding. We release the benchmark, codebase, and generation pipeline to support future research on multimodal assembly assistants grounded in real-world workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05515
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants
Huang, Haochen
Pei, Jiahuan
Aliannejadi, Mohammad
Sun, Xin
Ahsan, Moonisa
Yu, Chuang
Ren, Zhaochun
Cesar, Pablo
Wang, Junxiao
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grained spatial reasoning and precise object state detection are required. In this work, we explore LEGO Co-builder, a hybrid benchmark combining real-world LEGO assembly logic with programmatically generated multimodal scenes. The dataset captures stepwise visual states and procedural instructions, allowing controlled evaluation of instruction-following, object detection, and state detection. We introduce a unified framework and assess leading VLMs such as GPT-4o, Gemini, and Qwen-VL, under zero-shot and fine-tuned settings. Our results reveal that even advanced models like GPT-4o struggle with fine-grained assembly tasks, with a maximum F1 score of just 40.54\% on state detection, highlighting gaps in fine-grained visual understanding. We release the benchmark, codebase, and generation pipeline to support future research on multimodal assembly assistants grounded in real-world workflows.
title LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants
topic Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.05515