Architext: Language-Driven Generative Architecture Design

• URL: http://arxiv.org/abs/2303.07519v3
• Date: Wed, 3 May 2023 09:29:05 GMT
• Title: Architext: Language-Driven Generative Architecture Design
• Authors: Theodoros Galanos, Antonios Liapis and Georgios N. Yannakakis
• Abstract summary: Architext enables design generation with only natural language prompts, given to large-scale Language Models, as input. We conduct a thorough quantitative evaluation of Architext's downstream task performance, focusing on semantic accuracy and diversity for a number of pre-trained language models. Architext models are able to learn the specific design task, generating valid residential layouts at a near 100% rate.
• Score: 1.393683063795544
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Architectural design is a highly complex practice that involves a wide diversity of disciplines, technologies, proprietary design software, expertise, and an almost infinite number of constraints, across a vast array of design tasks. Enabling intuitive, accessible, and scalable design processes is an important step towards performance-driven and sustainable design for all. To that end, we introduce Architext, a novel semantic generation assistive tool. Architext enables design generation with only natural language prompts, given to large-scale Language Models, as input. We conduct a thorough quantitative evaluation of Architext's downstream task performance, focusing on semantic accuracy and diversity for a number of pre-trained language models ranging from 120 million to 6 billion parameters. Architext models are able to learn the specific design task, generating valid residential layouts at a near 100% rate. Accuracy shows great improvement when scaling the models, with the largest model (GPT-J) yielding impressive accuracy ranging between 25% to over 80% for different prompt categories. We open source the finetuned Architext models and our synthetic dataset, hoping to inspire experimentation in this exciting area of design research.

Related papers

• MetaDesigner: Advancing Artistic Typography through AI-Driven, User-Centric, and Multilingual WordArt Synthesis [65.78359025027457]
  MetaDesigner revolutionizes artistic typography by leveraging the strengths of Large Language Models (LLMs) to drive a design paradigm centered around user engagement. A comprehensive feedback mechanism harnesses insights from multimodal models and user evaluations to refine and enhance the design process iteratively. Empirical validations highlight MetaDesigner's capability to effectively serve diverse WordArt applications, consistently producing aesthetically appealing and context-sensitive results.
  arXiv  Detail & Related papers  (2024-06-28T11:58:26Z)
• PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM [58.67882997399021]
  Our research introduces a unified framework for automated graphic layout generation. Our data-driven method employs structured text (JSON format) and visual instruction tuning to generate layouts. We conduct extensive experiments and achieved state-of-the-art (SOTA) performance on public multi-modal layout generation benchmarks.
  arXiv  Detail & Related papers  (2024-06-05T03:05:52Z)
• Generative Design through Quality-Diversity Data Synthesis and Language Models [5.196236145367301]
  Two fundamental challenges face generative models in engineering applications: the acquisition of high-performing, diverse datasets, and the adherence to precise constraints in generated designs. We propose a novel approach combining optimization, constraint satisfaction, and language models to tackle these challenges in architectural design.
  arXiv  Detail & Related papers  (2024-05-16T11:30:08Z)
• I-Design: Personalized LLM Interior Designer [57.00412237555167]
  I-Design is a personalized interior designer that allows users to generate and visualize their design goals through natural language communication. I-Design starts with a team of large language model agents that engage in dialogues and logical reasoning with one another. The final design is then constructed in 3D by retrieving and integrating assets from an existing object database.
  arXiv  Detail & Related papers  (2024-04-03T16:17:53Z)
• Zero-Shot RTL Code Generation with Attention Sink Augmented Large Language Models [0.0]
  This paper discusses the possibility of exploiting large language models to streamline the code generation process in hardware design. The ability to use large language models on RTL code generation not only expedites design cycles but also facilitates the exploration of design spaces.
  arXiv  Detail & Related papers  (2024-01-12T17:41:38Z)
• From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Design [5.268919870502001]
  This paper presents a comprehensive evaluation of vision-language models (VLMs) across a spectrum of engineering design tasks. Specifically in this paper, we assess the capabilities of two VLMs, GPT-4V and LLaVA 1.6 34B, in design tasks such as sketch similarity analysis, CAD generation, topology optimization, manufacturability assessment, and engineering textbook problems.
  arXiv  Detail & Related papers  (2023-11-21T15:20:48Z)
• Opportunities for Large Language Models and Discourse in Engineering Design [0.0]
  We argue that discourse should be regarded as the core of engineering design processes, and therefore should be represented in a digital artifact. We describe how simulations, experiments, topology optimizations, and other process steps can be integrated into a machine-actionable, discourse-centric design process.
  arXiv  Detail & Related papers  (2023-06-15T14:46:44Z)
• MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks [59.09343552273045]
  We propose a decoder-only model for multimodal tasks, which is surprisingly effective in jointly learning of these disparate vision-language tasks. We demonstrate that joint learning of these diverse objectives is simple, effective, and maximizes the weight-sharing of the model across these tasks. Our model achieves the state of the art on image-text and text-image retrieval, video question answering and open-vocabulary detection tasks, outperforming much larger and more extensively trained foundational models.
  arXiv  Detail & Related papers  (2023-03-29T16:42:30Z)
• What Language Model to Train if You Have One Million GPU Hours? [54.32062236748831]
  We study the impact of different modeling practices and their impact on zero-shot generalization. We also study the performance of a multilingual model and how it compares to the English-only one. All our models and code are open-sourced at https://huggingface.co/bigscience.
  arXiv  Detail & Related papers  (2022-10-27T13:43:27Z)
• AIRCHITECT: Learning Custom Architecture Design and Mapping Space [2.498907460918493]
  We train a machine learning model to predict optimal parameters for the design and mapping space of custom architectures. We show that it is possible to capture the design space and train a model to "generalize" prediction the optimal design and mapping parameters. We train a custom network architecture called AIRCHITECT, which is capable of learning the architecture design space with as high as 94.3% test accuracy.
  arXiv  Detail & Related papers  (2021-08-16T05:05:52Z)
• XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation [80.18830380517753]
  We develop a new task-agnostic distillation framework XtremeDistilTransformers. We study the transferability of several source tasks, augmentation resources and model architecture for distillation.
  arXiv  Detail & Related papers  (2021-06-08T17:49:33Z)

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.