NVIDIA Releases Alpamayo 2 Super: A 34B Open Vision-Language-Action Model for Robotaxis and Autonomous Driving Under OpenMDW-1.1
MarkTechPosten
MarkTechPost
AI Global WireNVIDIA released Alpamayo 2 Super, a 34B vision-language-action model for autonomous driving, under OpenMDW-1.1 — a permissive license covering fine-tuning, derivatives and commercial redistribution. It pairs a 32B Cosmos 3 Super Reasoner backbone with a 2.3B diffusion action decoder, scores 79.2 on LingoQA, and emits trajectories, Chain-of-Causation traces, meta-actions, auto-labels and grounded VQA from a single pass. The post NVIDIA Releases Alpamayo 2 Super: A 34B Open Vision-Language-Action Model for Robotaxis and Autonomous Driving Under OpenMDW-1.1 appeared first on MarkTechPost .
This is a short summary published by AI Global Wire. The full article is owned and hosted by MarkTechPost — open it there to read it in full.
Read the full story at MarkTechPost- Verktyg
- Bild
- Robotik
Related AI news
- Black Forest Labs makes FLUX 3 Video generally available and claims it beats Seedance 2.0The Decoder · August 5, 2026
- Anthropic confirms it is building an in-house silicon team to design custom chips for Claude, co-designing hardware and models and using a "multi-chip approach" (Tom Carter/Business Insider)Techmeme · August 5, 2026
- Cloudflare launches Identity-Aware AI Gateway to track who is using AISiliconANGLE · August 5, 2026
- I've dictated over 120,000 words with my voice - these are my 3 favorite tools (and one is free)ZDNET AI · August 5, 2026
- Disputes over AI, robotics, trade mount ahead of planned Xi-Trump summit in USSCMP Tech · August 5, 2026
- Vectra AI launches Vectra AI Pro to feed AI agents better attack signalsSiliconANGLE · August 5, 2026