模型多源确认

SKY-001 工程世界模型发布,称在 CAD 和 BIM 任务上超越 GPT-6 Astra

精选理由

Maluuba 老团队做了个工程世界模型 SKY-001,CAD 和 BIM 任务上比 GPT-6 Astra 快上百倍还更便宜,做建筑设计的可以看看。

Sam Pasupalak 团队发布 SKY-001,定位为首个工程领域世界模型,历时 18 个月开发,团队来自被微软收购的 Maluuba 深度学习实验室。在 CAD 和 BIM 任务上,SKY-001 的速度比 GPT-6 Astra 等 frontier 模型快 51-125 倍,成本低 150-210 倍,IOU 指标更高。具体到 3D 建构任务,它以约 1/150 的单样本成本达到与 GPT-6 Astra 相当的准确率,BIM 任务提速超过 100 倍。作者认为世界模型是 LLM 之后的下一个前沿方向。

图片来源 · elvis
原文 · elvis

LLMs were just the beginning. Bullish on world models, and I think they are the next frontier in AI. Amazing to see a dedicated world model for engineering this early. SKY-001 against GPT-6 Astra matches accuracy on 3D construction at about 150x lower cost per sample. On BIM, it runs over 100x faster. Your browser does not support the video tag. 🔗 View on Twitter Sam Pasupalak @spisallyouneed Introducing SKY-001, the first Engineering World Model. On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested: -> 51-125x faster - > 150-210x cheaper -> Higher IOU than all frontier models SKY-001 lets you dream a physical object before you build it. 18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch ). The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 7 🔄 2 ❤️ 29 👀 2419 📊 9 ⚡