LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants

• URL: http://arxiv.org/abs/2507.05515v2
• Date: Wed, 23 Jul 2025 05:20:57 GMT
• Title: LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants
• Authors: Haochen Huang, Jiahuan Pei, Mohammad Aliannejadi, Xin Sun, Moonisa Ahsan, Chuang Yu, Zhaochun Ren, Pablo Cesar, Junxiao Wang,
• Abstract summary: We introduce a unified framework and assess leading Vision models under zero-shot and fine-tuned settings.<n>Our results reveal that even advanced models like GPT-4o struggle with fine-grained assembly tasks, highlighting gaps in fine visual understanding.
• Score: 22.6701800159627
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding [48.64661382961745]
  We introduce Spatio-temporal Video Action Grounding (SVAG), a novel task that requires models to simultaneously detect, track, and temporally localize all referent objects in videos.<n>To support this task, we construct SVAG-Bench, a large-scale benchmark comprising 688 videos, 19,590 annotated records, and 903 unique verbs.<n> Empirical results show that existing models perform poorly on SVAG, particularly in dense or complex scenes.
  arXiv  Detail & Related papers  (2025-10-14T22:10:49Z)
• Region-Level Context-Aware Multimodal Understanding [52.565528550835786]
  Region-level Context-aware Multimodal Understanding (RCMU) is an ability to integrate textual context associated with objects for a more context-aware multimodal understanding.<n>To equip MLLMs with RCMU capabilities, we propose Region-level Context-aware Visual Instruction Tuning (RCVIT)<n>We introduce the RCMU dataset, a large-scale visual instruction tuning dataset that covers multiple RCMU tasks.<n>We also propose RC&P-Bench, a comprehensive benchmark that can evaluate the performance of MLLMs in RCMU and multimodal personalized understanding tasks.
  arXiv  Detail & Related papers  (2025-08-17T07:18:43Z)
• RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation [80.20970723577818]
  We introduce RoboCerebra, a benchmark for evaluating high-level reasoning in long-horizon robotic manipulation.<n>The dataset is constructed via a top-down pipeline, where GPT generates task instructions and decomposes them into subtask sequences.<n>Compared to prior benchmarks, RoboCerebra features significantly longer action sequences and denser annotations.
  arXiv  Detail & Related papers  (2025-06-07T06:15:49Z)
• OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks [77.19223035769248]
  Recent breakthroughs in large multimodal models (LMMs) have demonstrated remarkable proficiency in following general-purpose instructions for image generation.<n>We introduce OmniGenBench, a novel benchmark meticulously designed to assess the instruction-following abilities of state-of-the-art LMMs.<n>Our OmniGenBench includes 57 diverse sub-tasks grounded in real-world scenarios, systematically categorized according to the specific model capabilities they demand.
  arXiv  Detail & Related papers  (2025-05-24T16:29:34Z)
• COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking [52.62149024881728]
  We propose a contrastive one-stage transformer fusion framework for vision-language (VL) tracking.<n>We introduce a contrastive alignment strategy that maximizes mutual information between a video and its corresponding language description.<n>By leveraging a visual-linguistic transformer, we establish an efficient multi-modal fusion and reasoning mechanism.
  arXiv  Detail & Related papers  (2025-04-02T03:12:38Z)
• MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models [34.138699712315]
  This paper introduces a novel vision--action (VLA) model, mixture of robotic experts (MoRE) for quadruped robots.<n>MoRE integrates multiple low-rank adaptation modules as distinct experts within a dense multi-modal large language model.<n>Experiments demonstrate that MoRE outperforms all baselines across six different skills and exhibits superior generalization capabilities in out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-03-11T03:13:45Z)
• EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents [63.43699771428243]
  EmbodiedBench is an extensive benchmark designed to evaluate vision-driven embodied agents.<n>We evaluated 24 leading proprietary and open-source MLLMs within EmbodiedBench.<n> MLLMs excel at high-level tasks but struggle with low-level manipulation, with the best model, GPT-4o, scoring only 28.9% on average.
  arXiv  Detail & Related papers  (2025-02-13T18:11:34Z)
• TRAVEL: Training-Free Retrieval and Alignment for Vision-and-Language Navigation [3.2688425993442696]
  We propose a modular approach for the Vision-Language Navigation (VLN) task by decomposing the problem into four sub-modules.<n>Given navigation instruction in natural language, we first prompt LLM to extract the landmarks and the order in which they are visited.<n>We generate path hypotheses from the starting location to the last landmark using the shortest path algorithm on the topological map of the environment.
  arXiv  Detail & Related papers  (2025-02-11T07:09:37Z)
• TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning [54.033346088090674]
  We introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding ability.<n>To fine-tune the model effectively, we generate a high-quality synthetic dataset we call SCOUT.<n>This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process.
  arXiv  Detail & Related papers  (2024-10-14T13:35:47Z)
• ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning [27.725814615823687]
  We propose a "plug-and-play" method, ExoViP, to correct errors in both the planning and execution stages. We employ verification modules as "exoskeletons" to enhance current vision-language programming schemes.
  arXiv  Detail & Related papers  (2024-08-05T03:22:10Z)
• MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding [59.41495657570397]
  We present a comprehensive dataset compiled from Nature Communications articles covering 72 scientific fields.<n>We evaluated 19 proprietary and open-source models on two benchmark tasks, figure captioning and multiple-choice, and conducted human expert annotation.<n>Fine-tuning Qwen2-VL-7B with our task-specific data achieved better performance than GPT-4o and even human experts in multiple-choice evaluations.
  arXiv  Detail & Related papers  (2024-07-06T00:40:53Z)
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs [61.143381152739046]
  We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach.<n>Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations.<n>We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes.
  arXiv  Detail & Related papers  (2024-06-24T17:59:42Z)
• RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image Understanding [4.266920365127677]
  Under the new LaGD paradigm, the old datasets are no longer suitable for fire-new tasks. We designed a high-quality, diversified, and unified multimodal instruction-following dataset for RSI understanding. The empirical results show that the fine-tuned MLLMs by RS-GPT4V can describe fine-grained information.
  arXiv  Detail & Related papers  (2024-06-18T10:34:28Z)
• NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision [64.83085920775316]
  We introduce NPHardEval4V, a multimodal benchmark suite grounded in four classical NP-hard problems.<n>Each task is presented through a combination of structured visual layouts and textual prompts, designed to assess the ability of LVLMs to perform reasoning under visual-linguistic constraints.<n>Our results show that while these models perform reasonably well on perception-based inputs, they struggle with global optimization, abstraction, and constraint satisfaction.
  arXiv  Detail & Related papers  (2024-03-04T07:10:31Z)
• Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions [11.786387517781328]
  Vision-Language Models (VLMs) are advanced models that can tackle more intricate tasks such as image captioning and visual question answering. Our classification organizes VLMs into three distinct categories: models dedicated to vision-language understanding, models that process multimodal inputs to generate unimodal (textual) outputs and models that both accept and produce multimodal inputs and outputs. We meticulously dissect each model, offering an extensive analysis of its foundational architecture, training data sources, as well as its strengths and limitations wherever possible.
  arXiv  Detail & Related papers  (2024-02-20T18:57:34Z)
• ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models [45.040292339670096]
  Large vision-language models (LVLMs) have shown premise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. This study aims to bridge the performance gap between traditional-scale LVLMs and resource-friendly lite versions by adopting high-quality training data.
  arXiv  Detail & Related papers  (2024-02-18T19:26:49Z)
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts [170.01089233942594]
  MathVista is a benchmark designed to combine challenges from diverse mathematical and visual tasks. The best-performing GPT-4V model achieves an overall accuracy of 49.9%, substantially outperforming Bard, the second-best performer, by 15.1%. GPT-4V still falls short of human performance by 10.4%, as it often struggles to understand complex figures and perform rigorous reasoning.
  arXiv  Detail & Related papers  (2023-10-03T17:57:24Z)
• All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment [39.54689489555342]
  Current vision-injected (VL) tracking framework consists of three parts, ie a visual feature extractor, a language feature extractor, and a fusion model.<n>We propose an All-in-One framework, which learns joint feature extraction and interaction by adopting a unified transformer backbone.
  arXiv  Detail & Related papers  (2023-07-07T03:51:21Z)
• LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark [81.42376626294812]
  We present Language-Assisted Multi-Modal instruction tuning dataset, framework, and benchmark. Our aim is to establish LAMM as a growing ecosystem for training and evaluating MLLMs. We present a comprehensive dataset and benchmark, which cover a wide range of vision tasks for 2D and 3D vision.
  arXiv  Detail & Related papers  (2023-06-11T14:01:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.