NVIDIA releases Alpamayo 2 Super, a 34B open VLA model targeting long-tail events in robotaxis

NVIDIA 发布 Alpamayo 2 Super：面向 Robotaxi 与自动驾驶的 34B 开源视觉-语言-动作模型

NVIDIA open-sourced Alpamayo 2 Super under a commercial license, targeting rare multi-agent driving scenarios. The 34B model combines a 32B VLM backbone (Cosmos 3 Super Reasoner, RL post-trained) with a 2.3B diffusion action decoder. From surround camera video it outputs a planned trajectory, a causal explanation, and a meta-action. Weights use OpenMDW-1.1, code is Apache 2.0, covering fine-tuning and commercial redistribution.

Why it matters: NVIDIA open-sourcing a 34B VLA for autonomous driving under a commercial license is directly relevant. HKR all hit, but the article is a MarkTechPost rewrite without first-hand testing or deployment details, so the score stays at 78 rather than higher.