NVIDIA DRIVE

Transforming transportation with #AI. Follow us for the latest in #autonomousvehicle development and news from our ecosystem.

[NVIDIA DRIVE @NVIDIADRIVE]

The #NVIDIAGTC 2026 keynote is officially LIVE! 🟢

Jensen Huang is on stage to unveil the latest breakthroughs in AI and accelerated computing. See how agentic AI, AI factories, and physical AI are powering the next generation of intelligent systems.

Watch now ⬇️ https://t.co/CPBOLwbnuU

[NVIDIA DRIVE @NVIDIADRIVE]

Robotaxi deployments are scaling, and safety can’t be an afterthought.

Automakers and developers need a software foundation that can support certified components, standardized interfaces, AI guardrails and validation before broader deployment.

NVIDIA Halos OS provides a production-ready safety foundation for AI-driven vehicles built on NVIDIA DRIVE Hyperion.

Learn more 👉 https://t.co/XCjSRQAolJ

[NVIDIA DRIVE @NVIDIADRIVE]

Generate Synthetic Data for Physical AI With NVIDIA Brev Launchables and Agent Skills https://t.co/M0MP2VIBuF

[NVIDIA DRIVE @NVIDIADRIVE]

Getting Started with NVIDIA Cosmos 3 for Robotics and Physical AI | Cosmos Labs https://t.co/jon44cjkUF

[NVIDIA DRIVE @NVIDIADRIVE]

We asked people around the NVIDIA office what they really think about robotaxis.

The answers: better vibes, safer rides, precise pickups, no parking, and no awkward small talk.

Watch the office takes, then learn how NVIDIA Halos OS helps build safety into AI-driven vehicles from the start: https://t.co/vzMjimx0ba

[NVIDIA DRIVE @NVIDIADRIVE]

The Alpamayo Summit at CVPR brought together AV researchers and industry leaders together under one room.

Hear from Marco Pavone (@drmapavone), Senior Director of Autonomous Vehicle Research, and other NVIDIA experts on how Alpamayo is accelerating AV development.

📺 Watch the on-demand replay: https://t.co/iE10sqlHbA

[NVIDIA DRIVE @NVIDIADRIVE]

We are at #CVPR2026 🙌

Each day, we’re recapping key NVIDIA research moments 👇

[NVIDIA DRIVE @NVIDIADRIVE]

We just wrapped the Alpamayo Summit at #CVPR2026.

A room full of autonomous vehicle researchers, builders, and partners came together to discuss what’s next — reasoning AI, simulation, safety, and an open ecosystem enabling the path to scalable level 4 autonomy.

From Alpamayo 2 Super to AlpaSim, AlpaGym, and new AV challenges, the conversation centered on closing the loop between research and real-world deployment.

Thanks to everyone who joined us in Denver.

[NVIDIA DRIVE @NVIDIADRIVE]

Introducing Alpamayo Recipes. 🧑‍🍳

A collection of end-to-end workflows for building, adapting, and deploying Alpamayo-based AV applications, v1, v1.5, and beyond.

✅ Alpamayo 1 SFT (HuggingFace Trainer + DeepSpeed)
✅ Alpamayo 1.5 SFT
✅ RL post-training via Cosmos-RL + GRPO
✅ Checkpoint conversion (v1 ↔ v1.5)
✅ Physical AI AV dataset download + curation

Whether you're experimenting locally or building a full production stack, this is your starting point.

🧑‍🍳 Recipes: https://t.co/wRKv7cTKvN
📄 Blog: https://t.co/uLjmMuc95R
🤗 Model: https://t.co/ElfDcP2JJ9

[Sanja Fidler @FidlerSanja]

Real time world model NVIDIA OmniDreams now open sourced!

If you are at CVPR, we invite you to also check out a live demo you can try out at the NVIDIA booth.

[NVIDIA DRIVE @NVIDIADRIVE]

AV partners are taking the stage at #CVPR2026.

@ForetellixHQ, @parallel_domain, and @LightwheelAI join NVIDIA researchers at Booth #211 to cover synthetic data, simulation, real-world disengagements, and what comes next for autonomous driving.

📅 June 5–6 | Denver Convention Center

🔗 Full schedule: https://t.co/KUI2VOTZwb

[NVIDIA DRIVE @NVIDIADRIVE]

We are helping autonomous vehicle researchers go beyond recorded miles.

At #CVPR2026, we unveiled new AV agent skills that help turn fleet data into editable 3D scenes, generate synthetic long-tail driving scenarios and evaluate policies in closed-loop simulation.

With Neural Reconstruction skills, NVIDIA AlpaGym and NVIDIA Alpamayo 2 Super, researchers can iterate across perception, planning and action for safer, scalable L4 development.

Learn more: https://t.co/JUBRFBnYeH

[NVIDIA DRIVE @NVIDIADRIVE]

We’re excited to share the expansion of NVIDIA Alpamayo, an open platform for developing reasoning-based autonomous vehicles.

👉 Alpamayo 2 Super: a 32B reasoning VLA model
👉 AlpaGym: closed-loop RL for AV training
👉 OmniDreams: photorealistic scenario generation
👉 Open models, datasets, and tools for the AV community

Check out @drmapavone's latest @HuggingFace blog:
https://t.co/subDOSIzWt

[Marco Pavone @drmapavone]

Excited to share the latest expansion of the @nvidia #Alpamayo open platform for reasoning-based autonomous vehicles.

Since its launch earlier this year, Alpamayo has seen rapid adoption across industry and academia, with its reasoning models surpassing 400,000 downloads and earning a #COMPUTEX 2026 Best Choice Award.

As announced by Jensen Huang during his #COMPUTEX keynote, we are now introducing several major additions designed to accelerate the development of next-generation AV systems (more details here: https://t.co/Xg0LYaEd9H):

🚗 Alpamayo 2 Super — a new 32B-parameter driving foundation model with:
• Full 360° surround-view perception
• Advanced reasoning capabilities and chain-of-causation outputs
• Meta-actions such as lane changes, yielding, and stopping
• Reasoning auto-labeling and visual grounding for scalable data annotation
• State-of-the-art performance across reasoning, prediction, and alignment tasks

🔄 AlpaGym — an open-source framework for closed-loop reinforcement learning, enabling AV models to learn from the consequences of their actions in simulation and helping bridge the gap between training and real-world deployment.

📊 New Open Benchmarks — including challenges for closed-loop driving and long-tail reasoning to help the community measure progress and drive innovation.

🛠️ Alpamayo Recipes — a centralized repository of end-to-end workflows covering supervised fine-tuning, reinforcement learning, quantization, and model customization.

Reasoning models and closed-loop training are becoming foundational technologies for autonomous systems. Our goal is to provide the open tools, models, infrastructure, and benchmarks needed to accelerate progress across the entire AV ecosystem.

A huge thank you to the many researchers, engineers, and community members whose feedback helped shape this release.

Resources:
• Overview of the latest Alpamayo release (note: some components will be released over the coming weeks): https://t.co/Xg0LYaEd9H
• @nvidia announcement: https://t.co/zWC2rbDK2W

#AutonomousVehicles #PhysicalAI #Robotics #AI #MachineLearning #ReinforcementLearning #OpenSource #NVIDIA #Alpamayo

@NVIDIADRIVE @NVIDIAAI

[NVIDIA DRIVE @NVIDIADRIVE]

@ForetellixHQ Love to see it! 👏

[NVIDIA DRIVE @NVIDIADRIVE]

What if you could hear what your car is thinking? 💭

This NVIDIA Alpamayo demo gives voice to the internal reasoning behind an autonomous drive — showing how the vehicle evaluates the road, plans its next move and adapts to city traffic while the driver enjoys the ride.

Watch the demo 👉 https://t.co/8SsRriGdwu

[NVIDIA DRIVE @NVIDIADRIVE]

Open-loop training can miss what happens after an AV model acts.

This technical blog shows how closed-loop post-training with NVIDIA Alpamayo helps AV policies learn from simulator feedback, surfacing compounding errors and failure modes that static datasets may miss.

Read the blog: https://t.co/V0LFLKCbxe

[NVIDIA DRIVE @NVIDIADRIVE]

“The ecosystem working with us to build L4 and robotaxis is expanding, and it’s going everywhere.” — Jensen Huang, Founder & CEO of NVIDIA

Robotaxis are moving from demos to deployment, powered by AI that can help vehicles drive, reason and operate safely at scale.

[NVIDIA DRIVE @NVIDIADRIVE]

Heading to #CVPR2026?

The Alpamayo Summit is currently at capacity, but you can still join the waitlist for a chance to attend this half-day workshop on Alpamayo, AlpaSim, the Physical AI AV dataset, and more.

Registered attendees will receive access to the replay.

Join the waitlist: https://t.co/ywWRfEiuD0