返回全部动态

NVIDIA发布开源VLA模型Alpamayo 2 Super,加速自动驾驶开发

原标题:Generate Trajectories, Reasoning Traces, and Auto-Labels with NVIDIA Alpamayo 2 Super

NVIDIA Technical Blog一手来源模型发布质量 85

AI 摘要

NVIDIA发布开源34B参数视觉-语言-动作模型Alpamayo 2 Super,用于加速自动驾驶开发。该模型结合Cosmos 3 Super Reasoner与扩散Action Expert,支持轨迹生成、推理、元动作预测及自动标注。在LingoQA基准上排名第一,超越多个更大模型。模型权重已开源,采用Linux基金会许可。

以上摘要由 AI 生成,可能存在误差。事实请以原文为准。

正文节选

Autonomous vehicle (AV) development often relies on separate models for trajectory generation, high-level intent prediction, scene understanding, and data labeling. This separation makes it hard to compare related outputs, investigate model behavior, and reuse the same representations across the development workflow. NVIDIA Alpamayo 2 Super is an open 34-billion-parameter reasoning vision-language-action (VLA) model designed to accelerate autonomous vehicle (AV) development. It combines the 32-b


发布时间:2026-08-04 23:00
抓取时间:2026-08-04 23:15
来源机构:NVIDIA
阅读原文developer.nvidia.com