做机器人抓取、自动驾驶或游戏 AI 的开发者，这三篇论文直接给出了可规模化训练的新思路——零样本抓取和紧凑推理方案值得重点关注。
NVIDIA 研究团队在 CVPR 2026 上展示了三篇关于物理 AI 的论文，分别针对零样本抓取、高效推理和具身智能体训练。GraspGen-X 是首个零样本抓取基础模型，基于数十亿次模拟抓取训练；LCDrive 用紧凑的潜在表示替代昂贵的文本推理；NitroGen 则是一个通用游戏 AI 基础模型，利用 NVIDIA Isaac GR00T 训练具身智能体。这些工作为大规模训练提供了突破性方案，覆盖了机器人操作、自动驾驶和游戏 AI 等关键领域。
Check out the NVIDIA blog!
Check out the NVIDIA blog! NVIDIA @nvidia This week at #CVPR2026 , NVIDIA Research is presenting three papers across physical ai that offer groundbreaking solutions for training at scale across diverse applications: → GraspGen-X: the first foundation model for zero-shot grasping, trained on billions of simulated grasps → LCDrive: a model that replaces expensive text-based reasoning with compact latent representations → NitroGen: a generalized gameplay AI foundation model that harnesses NVIDIA Isaac GR00T to help train embodied agents Learn more: nvda.ws/4ubwjgk Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 1 🔄 2 ❤️ 9 👀 4608 📊 2 ⚡