LLM4DESIGN: An Automated Multi-Modal System for Architectural and Environmental Design

2024-06-28 · Ran Chen, Xueqi Yao, Xuhui Jiang

This study introduces LLM4DESIGN, a highly automated system for generating architectural and environmental design proposals. LLM4DESIGN, relying solely on site conditions and design requirements, employs Multi-Agent systems to foster creativity, Retrieval Augmented Generation (RAG) to ground designs in realism, and Visual Language Models (VLM) to synchronize all information. This system resulting in coherent, multi-illustrated, and multi-textual design schemes. The system meets the dual needs of narrative storytelling and objective drawing presentation in generating architectural and environmental design proposals. Extensive comparative and ablation experiments confirm the innovativeness of LLM4DESIGN's narrative and the grounded applicability of its plans, demonstrating its superior performance in the field of urban renewal design. Lastly, we have created the first cross-modal design scheme dataset covering architecture, landscape, interior, and urban design, providing rich resources for future research.

📄 PDF Abstract BibTeX arXiv:2407.12025

Code (0)

등록된 구현이 없습니다.

Tasks

RAG RetrievalRetrieval-augmented Generation

LEMUR 2: Unlocking Neural Network Diversity for AI

2026-07-07 · Tolgay Atinc Uzun, Waleed Khalid, Saif U Din, Sai Revanth Mulukuledu 외 arxiv

Existing NAS benchmarks (e.g., NAS-Bench, NATS-Bench) cover only narrow, task-specific regions of the architectural design space and lack cross-domain or deployment-aware evaluation. LEMUR 2 introduces a large-scale, ext…

Image Captioning

Multimodal Cultural Heritage Architectural Style Classification for Residential Buildings in the UAE Based on CLIP Embeddings and SVM

2026-09-15 · Ahmed Ammar Kubba, Manar Abu Talib, Iman Ibrahim, Qassim Nasir arxiv

The analysis and classification of cultural heritage architectural styles remain challenging due to the complexity of visual images of buildings, which are highly relied on in traditional CNN-based classification approac…

Dimensionality Reduction

Social Caption: Evaluating Social Understanding in Multimodal Models

2026-01-21 · Leena Mathur, Bhaavanaa Thumu, Youssouf Kebe, Louis-Philippe Morency arxiv

Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce SOCIAL CAPTION, a framework grounded in interaction theory to evaluate social u…

Composing Recurrent Spiking Neural Networks using Locally-Recurrent Motifs and Risk-Mitigating Architectural Optimization

2021-08-04 · Wenrui Zhang, Hejia Geng, Peng Li

In neural circuits, recurrent connectivity plays a crucial role in network function and stability. However, existing recurrent spiking neural networks (RSNNs) are often constructed by random connections without optimizat…

Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspective

2024-12-23 · Kaifang Long, Guoyang Xie, Lianbo Ma, Jiaqi Liu 외

Existing efforts to boost multimodal fusion of 3D anomaly detection (3D-AD) primarily concentrate on devising more effective multimodal fusion strategies. However, little attention was devoted to analyzing the role of mu…

3D Anomaly Detection Anomaly Detection Neural Architecture Search