Tag
Anthropic announces Fable 5, a state-of-the-art model for mechanical engineering tasks capable of generating intricate assemblies and mechanisms from a single prompt.
This paper presents a modular impact diverting mechanism for football helmets, aiming to improve safety by redirecting impact forces.
This paper proposes VFEAgent, a multi-agent system that automates finite element analysis by integrating vision-language models with a verification-first code synthesis framework, enabling end-to-end simulation from images and problem descriptions.
This paper introduces MechVQA, a dataset with 3.3k high-density mechanical engineering drawings and 21k question-answer pairs, along with the MechVL model that outperforms existing baselines by 7.57 percentage points on the MechVQA total score, advancing multimodal LLM understanding of mechanical drawings.
Gemini 3 Deep Think enables faster mechanical design iteration by generating multiple design options from images or prompts, helping non-CAD experts rapidly explore and prototype.