Tag
提出SNTO框架，将状态、伴随和设计变量用神经网络联合表示并优化，结合多GPU硬件感知训练，实现可扩展的应力约束拓扑优化，可处理高达八百万配置点的三维大规模问题。
一项评估通用AI模型（以GPT-6 Astra为案例）在工程CAD任务中能力的研究，涵盖CAD理解、生成、编辑与评估。研究发现通用AI模型开始在工程设计中展现实用价值，但在几何有效性、装配可行性与参数化可编辑性等工程可靠性方面仍存在重大挑战。
RAC 提出了一种与执行框架无关的“关系型智能体合约”，让智能体只声明语义关系、由专用工具推导具体实现，并在 PCB 设计、作业车间调度和嵌入式代码任务上显著提升了约束满足率（如 PCB 平均 90.9% 对比 74.0%）。
This paper presents a novel framework that integrates a frozen text-to-image diffusion model as a training-free prior into topology optimization, enabling engineers to express design intent through natural language prompts and achieving significant compliance reductions in structural design.
PhysicsBench introduces a unified benchmark and leaderboard to standardize the evaluation of generative and predictive AI models for engineering design and simulation across multiple tasks and data scales.
Researchers from MIT and others developed GIFT, a system that teaches vision-language models to automatically convert 2D designs into accurate CAD programs for rapid prototyping, using model-generated data to correct mistakes and improve performance with less computation.
This paper proposes automation-in-design (AiD) using computational design synthesis with deep learning and generative AI to automate the creation of novel high-tech systems, demonstrated in two case studies (e-drive and spatial dimensioning).
BIM-Edit is a benchmark for evaluating LLMs on natural-language editing of Building Information Models (BIM) in IFC format. Results show a substantial gap, with the best model achieving only 49.5% average score across geometric, semantic, and topological metrics.
This paper proposes eCNNTO, a CNN with residual connections to accelerate density-based topology optimization by predicting near-optimal densities from early iteration histories, achieving up to 97% reduction in iterations and strong generalization across different boundary conditions, geometries, and mesh resolutions.
EngiAI introduces a multi-agent framework and benchmark suite for LLM-driven engineering design, evaluating workflow, RAG, and HPC dimensions. Proprietary models achieve 96-97% task completion on Beams2D, while conditional branching remains challenging with 20-53% for Photonics2D.