Wenhao Ding

Research Scientist @NVIDIA | Ph.D.@CarnegieMellon | B.E. @tsinghua_uni

[NVIDIA @nvidia]

NVIDIA Alpamayo 2 Edge is here, bringing adaptive AI reasoning in real-time to the vehicle. 🚘

From yielding to pedestrians to making room for an oncoming bus, watch how it plans driving paths and explains its decisions when needed.

Developers can build on this open model to create the next generation of autonomous vehicles, with AI they can adapt to their own fleets.

[Wenhao Ding @wenhaoding95]

Come check out our demo at CoRL!

[Marco Pavone @drmapavone]

@nvidia Alpamayo has pioneered #reasoning-based autonomy. Now, we’re expanding the capabilities of the Alpamayo open platform to enable long-horizon autonomy for any robot in the real world—from vehicles and mobile manipulators to humanoids.

At #CoRL2026, we’re excited to showcase a proof point of what the platform enables: agentic, reasoning-based whole-body intelligence for humanoids.

Stop by our demo to see it in action and explore what we can build together with the Alpamayo open platform. And stay tuned for an exciting announcement later this week!

🗓️ Tuesday, November 10 | 10:00 AM–6:30 PM CT
📍 Booth 4, Lone Star Ballroom, JW Marriott Austin

CoRL demo program: https://t.co/dyQM3fTE0i

#Alpamayo #PhysicalAI #Robotics #CoRL2026

@NVIDIAAI @NVIDIARobotics @NVIDIADRIVE

[Marco Pavone @drmapavone]

@nvidia Alpamayo has pioneered #reasoning-based autonomy. Now, we’re expanding the capabilities of the Alpamayo open platform to enable long-horizon autonomy for any robot in the real world—from vehicles and mobile manipulators to humanoids.

At #CoRL2026, we’re excited to showcase a proof point of what the platform enables: agentic, reasoning-based whole-body intelligence for humanoids.

Stop by our demo to see it in action and explore what we can build together with the Alpamayo open platform. And stay tuned for an exciting announcement later this week!

🗓️ Tuesday, November 10 | 10:00 AM–6:30 PM CT
📍 Booth 4, Lone Star Ballroom, JW Marriott Austin

CoRL demo program: https://t.co/dyQM3fTE0i

#Alpamayo #PhysicalAI #Robotics #CoRL2026

@NVIDIAAI @NVIDIARobotics @NVIDIADRIVE

[Wenhao Ding @wenhaoding95]

Glad to share that our recent work, AlpaJudge for driving reasoning evaluation, was released at #GTCBerlin! Please try it on GitHub https://t.co/M7zFB4c4zT. Details of this model can be found in the VeriFine paper: https://t.co/wgEzq04w75

[Marco Pavone @drmapavone]

What if AI could improve not only its own policies, but also the judges that evaluate them?

As AI policies improve, they encounter new challenges and develop new failure modes. The judges evaluating them need to evolve as well. Otherwise, they can become a bottleneck to further progress. This is particularly relevant for #Physical #AI, where good decisions require spatial grounding, causal reasoning, and safety awareness.

In our new paper, we introduce VeriFine, an #agentic #harness for continuous self-improvement in Physical AI, where policies, training curricula, and judges evolve together.

The idea is to build agentic systems that can identify policy failures, turn them into useful training signals, and improve the policy. When the judge itself becomes a bottleneck, the harness brings in targeted human feedback to refine its evaluations and guide the next round of improvement.

We evaluate VeriFine on autonomous driving and robot navigation, demonstrating continued improvements in both policy and judge capabilities through reinforcement learning and supervised fine-tuning.

Key takeaway: We're developing agentic harnesses that go beyond optimizing a policy in a fixed loop. They adapt the improvement process itself—including how failures are identified, how training data is selected, and how progress is evaluated.

📄 Paper: https://t.co/NckfQWdqLQ
🌐 Website: https://t.co/8SSi8mFsPq

Work led by Zewei Zhou, in collaboration with Rachel Luo Yulong Cao @ChaoweiX Chensheng Peng @Boyiliee @tianran_ Zheng Lian @yan_wang_9 Jiaqi Ma @iamborisi @wenhaoding95

#PhysicalAI #Robotics #AgenticAI #Alpamayo

@NVIDIADRIVE @NVIDIAAI

[Wenhao Ding @wenhaoding95]

Co-evolving judge models bridge the policy model to human intent and boost policy performance with minimal human effort. Thanks @Zewei__Zhou for your amazing work during your internship! 💚

[Zewei Zhou @Zewei__Zhou]

🤔 𝘾𝙖𝙣 𝙨𝙚𝙡𝙛-𝙞𝙢𝙥𝙧𝙤𝙫𝙚𝙢𝙚𝙣𝙩 𝙗𝙚 𝙨𝙪𝙨𝙩𝙖𝙞𝙣𝙚𝙙 𝙬𝙞𝙩𝙝 𝙖 𝙛𝙞𝙭𝙚𝙙, 𝙣𝙤𝙣-𝙘𝙤-𝙚𝙫𝙤𝙡𝙫𝙞𝙣𝙜 𝙟𝙪𝙙𝙜𝙚?

Better policies expose new failures. If their judges stay fixed, verification can become the bottleneck to further self-improvement.

[Wenhao Ding @wenhaoding95]

We’re hiring research interns to work on foundation models and reasoning for Physical AI, spanning both humanoid robotics and autonomous driving. This is not limited to summer internships - start dates are flexible throughout 2027. Please apply if you’re interested!

[Marco Pavone @drmapavone]

We are hiring! The Autonomous Systems and Physical AI Research (ASPIRE: https://t.co/HZF2dnxUBf) group at @nvidia is looking for talented PhD Research Interns to join us in advancing the frontiers of #autonomous #systems and #Physical #AI.

We work across a broad range of research areas, including #reasoning models, generative simulation, #agentic AI workflows, and Physical AI #safety, with applications spanning autonomous vehicles and a broad range of Physical AI systems.

Interested in pushing the limits of what’s possible? Apply now:
https://t.co/QGQbgCl5Lu

[Wenhao Ding @wenhaoding95]

Proud to see our work shared by Jensen! Training a 32B model for physical AI is not easy. I learned a lot throughout the journey, and I'm thrilled we made it happen. More iteration are ahead as we continue building stronger, more capable open-sourced physical AI models.

[Jensen Huang @JensenHuang]

Today, we’re launching Alpamayo 2 Super, our frontier open reasoning model for autonomous vehicles.

Beyond seeing, Alpamayo understands and reasons through the complex world - thinks before it acts.

It’s a powerful backbone for robotaxis, trucks, shuttles, delivery vans, tractors and the long tail of mobile robots—billions of autonomous machines someday.

We’re releasing it for commercial use under OpenMDW-1.1 so teams can inspect it, fine-tune it and deploy it—open models advance safety and security.

The next wave of AI is robotics—and it starts with autonomous vehicles.

Great work, Alpamayo team!

https://t.co/2PYCCXWjZh

[Marco Pavone @drmapavone]

How do we make robot policies robust to rare but high-impact failures?

Video #World #Models (WMs) are rapidly becoming a powerful tool for robotics, enabling policy evaluation and improvement by "imagining" future outcomes. But there's a catch: these imagined futures are typically nominal samples, making it easy to overlook the rare yet safety-critical events that matter most.

In our new paper, StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement, we explore a simple but powerful idea:

💡 Instead of passively sampling futures, actively steer world model imaginations toward high-impact yet still plausible scenarios.

StressDream optimizes the initial diffusion noise at inference time, allowing us to generate targeted stress-test scenarios without retraining the world model. This enables:
- More robust policy evaluation by exposing failure modes that random sampling often misses.
- Improved policy optimization by training against challenging but realistic imagined futures.

As generative world models become a foundation for #Physical #AI, the ability to systematically probe their "long tail" of plausible futures will be increasingly important for building reliable and trustworthy autonomous systems.

📌 𝖯𝗋𝗈𝗃𝖾𝖼𝗍 𝖯𝖺𝗀𝖾: https://t.co/0BSM0d0X0n
📄 𝖯𝖺𝗉𝖾𝗋: https://t.co/JQ3Ij4SZWY

Work led by Junwon Seo, with a great set of collaborators: Sushant Veer, Thomas Ran Tian, Wenhao Ding, Apoorva Sharma, Karen Leung, Edward Schmerling, Andrea Bajcsy.

@NVIDIADRIVE @NVIDIAAI

#Robotics #WorldModels #PhysicalAISafety #AISafety #AutonomousSystems #RobotLearnin

[Marco Pavone @drmapavone]

Today we're releasing @nvidia AlpaGym, our new open-source reinforcement learning (RL) framework for end-to-end autonomous driving.

A key challenge for #Physical #AI is enabling policies to learn from the consequences of their actions. While supervised learning can teach a model to imitate behavior, robust autonomy ultimately requires learning through interaction with the environment.

AlpaGym enables exactly that.

Built on top of:
- AlpaSim: our high-fidelity closed-loop autonomous driving simulator
- Cosmos-RL: NVIDIA's distributed RL training and rollout infrastructure

AlpaGym provides the glue that connects simulation, training, and driving policies into a scalable framework for post-training autonomous vehicle models in closed loop.

With AlpaGym, researchers and developers can:
✅ Train end-to-end driving policies using reinforcement learning
✅ Run large-scale closed-loop simulations
✅ Experiment with new reward functions, policy architectures, and training strategies
✅ Benchmark models on public leaderboards

📖 Learn how it works: https://t.co/9iJYY1bSMq

💻 GitHub: https://t.co/j5Zuu4af0n

🏆 Open Challenges:
- AlpaSim Closed-Loop E2E Driving Challenge: https://t.co/fR60fwcDQT
- Physical AI AV Reasoning Challenge: https://t.co/3L7TGnV4R2

Learn more about the #Alpamayo open platform:
https://t.co/Xg0LYaEd9H

#PhysicalAI #AutonomousDriving #ReinforcementLearning #Robotics #OpenSource #NVIDIA #MachineLearning

@NVIDIADRIVE @NVIDIAAI

[Junwon Seo ✈️ CoRL @Junwon__Seo]

Video world model imaginations🌎💭can miss critical but plausible outcomes of robot actions.

Introducing 𝙎𝙩𝙧𝙚𝙨𝙨𝘿𝙧𝙚𝙖𝙢: inference-time steering for video WMs, imagining plausible✅, high-impact⚠️ futures for 𝙧𝙤𝙗𝙪𝙨𝙩🛡️ policy evaluation and improvement.

(1/15)

[Changyi Lin @changyi_lin1]

Manipulation happens through surfaces. To understand contact-rich dexterous interaction, motion alone is not enough. We also need to know surface properties and contact state.

Excited to share ART-Glove, an articulated tactile glove that captures contact-grounded information while preserving human dexterity. It provides:

- Known Geometry: 16 rigid functional surfaces
- Surface Motion: 22 anatomically aligned joints
- Tactile Contact: 2048 piezoresistive taxels

Huge thanks to my advisor Ding @zhao__ding, and to Yuxiang @yxyang1995, Maria @bauzavillalonga, Marissa, and Peide @peide_huang for the valuable advice and discussions.

Paper: https://t.co/xSYCyqHrZf

[Yue Wang @yuewang314]

Introducing Ψ₀ (https://t.co/qqH1PiIJS8) — an open foundation model for universal humanoid loco-manipulation.

🏆 Outperforms GR00T N1.6 by 40%+ overall success rate
📉 Uses only ~10% of the pre-training data
📦 Fully open-source: model, data, code, and deployment pipeline

1/10

[Wenhao Ding @wenhaoding95]

Our Alpamayo model has a major update! Stay tuned for the code and model release

[Marco Pavone @drmapavone]

Jensen today announced Alpamayo 1.5 at #NVIDIAGTC!

#Alpamayo 1.5 is a major update to Alpamayo 1—@nvidia’s open 10B-parameter chain-of-thought reasoning VLA model, first introduced at #CES. Built on the #Cosmos-Reason2 VLM backbone and post-trained with RL, it adds support for navigation guidance, flexible multi-camera setups, configurable camera parameters, and user question answering. The result is an interactive, steerable reasoning engine for the AV community. We’re also releasing post-training scripts to help researchers and developers adapt the model.

Additionally, we’ve significantly expanded the Alpamayo open platform across data and simulation, including releasing highly requested reasoning labels for the PhysicalAI Autonomous Vehicles dataset (https://t.co/fD9eUcndya), as well as our chain-of-causation auto-labeling pipeline.

🔎 Learn more about Alpamayo 1.5 and the latest extensions to the Alpamayo open platform:
https://t.co/P0nuqkwBab (please note that most of the links will become active in the next few days.)

Happy building—and stay tuned for more in the coming months!

@NVIDIADRIVE @NVIDIAAI

[Marco Pavone @drmapavone]

What does it take to build autonomous vehicles that can reason about the world they drive in?

Tomorrow at #NVIDIAGTC, Patrick Liu and I will take a deep dive into the #Alpamayo #reasoning model family—a family of reasoning-based vision–language–action (#VLA) models that form a core component of the Alpamayo open platform (https://t.co/EmY9IRNXHZ).

We’ll cover three main topics:
- How reasoning-based VLA models like Alpamayo 1 are designed and built
- What it takes to bring Alpamayo 1 to production, including some of our latest results
- Several exciting announcements about the expansion of the Alpamayo open platform

If you're working on autonomous driving, robotics, or foundation models for physical AI, this session will offer a look at where the field is heading.

Session details:
📅 Monday, Mar 16 | 3:00 PM PDT
📍 #NVIDIAGTC 2026
🔗 https://t.co/ZJk5GGIbFV

Looking forward to seeing many of you there.

@NVIDIADRIVE @NVIDIAAI

[NVIDIA DRIVE @NVIDIADRIVE]

Alpamayo 1 is now @huggingface’s top-downloaded robotics model with 100K downloads and counting. 🎉

It helps researchers and autonomous-driving practitioners develop and evaluate vision-language-action models for complex autonomous-driving scenarios, especially rare long-tail events.

🔗 Get started with Alpamayo 1 today: https://t.co/QUrhHkZMbF
🎥 Watch the deep-dive: https://t.co/sxceaDLIjc

[Wenhao Ding @wenhaoding95]

Checkout the replay of the livestrem to learn more about how we design and build alpamayo 1!

[NVIDIA DRIVE @NVIDIADRIVE]

💨 How fast can an autonomous vehicle think?

With Alpamayo 1, NVIDIA's 10B-parameter chain-of-thought reasoning model, the distilled version can reason in real time.

Hear Marco Pavone (@drmapavone), Yan Wang, Yurong You, and Wenhao Ding from our AV Research team break down Alpamayo 1 and what's next for reasoning in autonomous driving.

🔁 Watch the replay: https://t.co/q3YcMjoFsn

[Marco Pavone @drmapavone]

Join me and my collaborators for a *live* discussion on @nvidia Alpamayo 1 (https://t.co/9nI9L08LJJ), a reasoning-based vision–language–action (VLA) model for autonomous driving.

🎥 Livestream: Inside NVIDIA Alpamayo 1: Making Autonomous Vehicles Reason
🗓 February 11
⏰ 9:00am PST
📍 Watch here: https://t.co/WJkK2AaTkF

As NVIDIA CEO Jensen Huang put it:
“The ChatGPT moment for physical AI is here — when machines begin to understand, reason, and act in the real world. Robotaxis are among the first to benefit. Alpamayo brings reasoning to autonomous vehicles, allowing them to think through rare scenarios, drive safely in complex environments, and explain their driving decisions — it’s the foundation for safe, scalable autonomy.”

During the livestream, we’ll cover:
- How #reasoning-based #VLA models like #Alpamayo 1 are designed and built
- Applications ranging from end-to-end #autonomy to reasoning-driven auto-labeling
- Key opportunities and challenges in developing reasoning models for #Physical #AI

I’ll be joined by core Alpamayo 1 developers @yan_wang_9 @YurongYou @wenhaoding95, and we’ll take questions live from the community.

📖 Ahead of time, you might enjoy this overview of the Alpamayo ecosystem:
https://t.co/EmY9IRNXHZ

And if you’re attending @NVIDIAGTC (March 16–19) and would like to meet some of the Alpamayo team in person, you can use my employee code for 25% off your conference pass:
https://t.co/Qd3JkaMBIK

Hope to see you at the livestream!

@NVIDIAAI @NVIDIADRIVE

[Marco Pavone @drmapavone]

It’s incredibly exciting to see how quickly the community is engaging with the @nvidia Alpamayo ecosystem for developing reasoning-based autonomous vehicles (https://t.co/EmY9IRNpSr)!

In this instance, TIER IV is showcasing Alpamayo 1’s reasoning capabilities in Tokyo, integrated with Autoware and ROS. Fantastic work, @ShinpeiKato and the @tier_iv_global team! 👏

Quick highlights about Alpamayo:

Alpamayo 1:
- Among HuggingFace’s top 10 overall trending models
- Among the top 3 most downloaded models on HuggingFace when filtered by 'robotics'

Alpamayo PhysicalAI–Autonomous-Vehicles dataset:
- Trending in HuggingFace’s top 10 overall datasets

Happy developing! 🚀

#AutonomousVehicles #Robotics #AI #Reasoning #HuggingFace #Autoware #ROS #AutonomousDriving #PhysicalAI #Alpamayo #RobotLearning @NVIDIAAI @NVIDIADRIVE

[Marco Pavone @drmapavone]

More on #reasoning in Vision-Language-Action (#VLA) models --- Traditional VLA models decide what action to take by decomposing complex situations into their most salient factors. But reasoning models can do much more. When viewed as implicit world models operating in a semantic space, they can be used counterfactually—exploring multiple “what if” scenarios before acting.

In our recent paper, Counterfactual VLA (CF-VLA, https://t.co/IMk9CWQ2Zx), we show that counterfactual reasoning consistently improves trajectory accuracy, safety, and reasoning quality.

Key contributions:
- Self-reflective counterfactual reasoning: CF-VLA reflects on predicted meta-actions, anticipates consequences, and revises plans before execution—enabling causal self-correction.

- Automated data pipeline: A novel data pipeline generates counterfactual data, forming a self-improving loop for reasoning and action.

- Adaptive thinking in autonomous driving: CF-VLA focuses reasoning on the most challenging scenarios, improving performance while keeping test-time computation efficient.

Paper: https://t.co/IMk9CWQ2Zx

#AI #Robotics #VisionLanguageAction #AutonomousSystems #MachineLearning #CounterfactualReasoning @NVIDIAAI @NVIDIADRIVE