paper-with-me

Papers

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

2025-07-07 · Haochen Huang, Jiahuan Pei, Mohammad Aliannejadi, Xin Sun, Moonisa Ahsan, Chuang Yu, Zhaochun Ren, Pablo Cesar, Junxiao Wang arxiv

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. We also evaluated the framework using a reasoning-focused model, GLM-4.1-thinking. Our results show that while object detection achieved high performance (98.16% with fine-tuned InstructBLIP), fine-grained scene understanding and assembly state detection remain challenging: Fine-tuned MiniGPT-v2 reached only 37.52% F1 for identifying theme entities, and even advanced models such as GPT-4o achieved just 40.54% F1 on state detection. This highlights gaps in fine-grained visual understanding among existing models. We release the benchmark, codebase, and generation pipeline to support future research on multimodal assembly assistants grounded in real-world workflows.

📄 PDF Abstract BibTeX arXiv:2507.05515

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial ReasoningObject Detection

Similar Papers 제목 키워드 기반

Lego-Edit: A General Image Editing Framework with Model-Level Bricks and MLLM Builder

2025-09-16 · Qifei Jia, Yu Liu, Yajie Chai, Xintong Yao 외 arxiv

Instruction-based image editing has garnered significant attention due to its direct interaction with users. However, real-world user instructions are immensely diverse, and existing methods often fail to generalize effe…

Reinforcement LearningImage ManipulationImage Editing

LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision

2021-12-18 · Rui Han, Qinglong Zhang, Chi Harold Liu, Guoren Wang 외

Deep neural networks (DNNs) have become ubiquitous techniques in mobile and embedded systems for applications such as image/object recognition and classification. The trend of executing multiple DNNs simultaneously exace…

Knowledge DistillationModel CompressionObject Recognition

LEGO-Eval: Towards Fine-Grained Evaluation on Synthesizing 3D Embodied Environments with Tool Augmentation

2025-11-04 · Gyeom Hwangbo, Hyungjoo Chae, Minseok Kang, Hyeonjong Ju 외 arxiv

Despite recent progress in using Large Language Models (LLMs) for automatically generating 3D scenes, generated scenes often lack realistic spatial layouts and object attributes found in real-world environments. As this …

Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality

2024-05-16 · Jiahuan Pei, Irene Viola, Haochen Huang, Junxiao Wang 외

Autonomous artificial intelligence (AI) agents have emerged as promising protocols for automatically understanding the language-based environment, particularly with the exponential development of large language models (L…

Mixed RealityQuestion Answering

LEGO: An LLM Skill-Based Front-End Design Generation Platform

2026-04-25 · Jincheng Lou, Ruohan Xu, Jiecheng Ma, Runzhe Tao 외 arxiv

Existing LLM-based EDA agents are often isolated task-specific systems. This leads to repeated engineering effort and limited reuse of successful design and debugging strategies. We present LEGO, a unified skill-based pl…