NVIDIA 发布 VFlash:面向 Physical AI 的 System-1 视觉语言模型
Website: https://t.co/nQodFamRAR Please check out project lead @ZhidingYu's deep dive post! https:...
NVIDIA 的 Jim Fan 团队出了个 VFlash,让机器人用视觉规划快速反应,技术解读帖写得很细,做具身的可以看看。
NVIDIA 的 LPR 团队与 GEAR Lab(Jim Fan)联合推出 VFlash,定位为面向 Physical AI 的 System-1 视觉语言模型。项目负责人 Zhiding Yu 表示,具身模型可以以视觉规划的形式快速思考,而非仅在文本中推理。项目页面已上线 research.nvidia.com,团队还发布了详细的技术解读推文串。合作者包括 YuCheng Chou、Shihao Wang 和 Jin Huang。
Website: https://t.co/nQodFamRAR Please check out project lead @ZhidingYu's deep dive post! https:...
Website: research.nvidia.com/labs/lpr/vflas… Please check out project lead @ZhidingYu 's deep dive post! x.com/ZhidingYu/stat… Zhiding Yu @ZhidingYu Embodied models don't just think in text, they can think in visual plans, and fast. Introducing VFlash, System-1 VLM for Physical AI. Joint work by @YuCheng_Chou_ , Shihao Wang and Jin Huang, LPR Team ( @jankautz ), GEAR Lab ( @DrJimFan ), and many other collaborators. 🌐 Website: research.nvidia.com/labs/lpr/vflas… P 🧵[1/8] More details in the thread👇 Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 1 🔄 2 ❤️ 12 👀 2479 📊 2 ⚡