Applied Intuition

Applied Intuition is the physical AI company bringing intelligence to every moving machine on the planet.

[Applied Intuition @AppliedInt]

Where does physical AI go from here? @qasar shares his takes with @eostudi0.

Watch the full episode: https://t.co/wsmpsMPcqb

[Qasar Younis @qasar]

Everyone’s been talking about Mission S vs flying Roadsters and the physical part of their design BUT the human-machine interaction matters just as much, if not more.

Like you see and interact with your car from the inside most of the time. So then why are most in cabin experiences far from magical, seamless AI driven interactions? Because historically there wasn’t a platform to build on

[Applied Intuition @AppliedInt]

When software shapes the car, what’s left for design?

The human. See how we’re building the next generation of intelligent cars with @Stellantis.

https://t.co/2NFEkVAu3K

[Qasar Younis @qasar]

Simulation is still our bread and butter and it’s only becoming clearer that it’ll unlock robotics at scale

[Wei ZHAN @Wei_ZHAN_]

Reinforcement Learning (RL) in simulation is a scalable strategy to learn dexterous skills, but naive exploration from scratch often fails to discover manipulation strategies for diverse objects.

At @AppliedInt, we propose X-Reset, a straightforward method to resolve the exploration problem for generalist RL policies by randomly sampling resets from human hand-object states.
- We train a single dexterous policy to manipulate a variety of objects to any goal pose, ranging from small markers to heavy powerdrills with zero teleoperation data
- The learned policy zero-shot generalizes well beyond the training set (DexYCB), and transfers from sim-to-real using object pose-tracking models

We are continuously expanding robotics research at @AppliedInt beyond X-Reset, with the bounds of simulation and synthetic data for dexterous manipulation pushed. Stay tuned and join us!

🌐 Project Page: https://t.co/xEXMnWxja2
📄 Paper: https://t.co/28Ewh0pUYS

[Applied Intuition @AppliedInt]

Dexterous manipulation in simulation has an exploration problem.

Here is how our team is fixing this problem.

[Prithwish Dan @prithwish_dan]

Exploration is hard for RL when training high-DoF dex hands ✋

X-Reset makes generalist object-centric RL easier by resetting to human hand-object states 🙋‍♀️

We mitigate the exploration problem, and train a single policy to manipulate a variety of objects to any goal pose 🧵

[EO @eostudi0]

“I don’t believe you can be very successful and not read a lot.”

4 books @qasar recommends, the ones that helped him build @AppliedInt, a $15B physical AI company:

📍I Am That, Sri Nisargadatta Maharaj
📍Sam Walton: Made in America, Sam Walton (with John Huey)
📍The Story of My Experiments with Truth, Mahatma Gandhi
📍Long Walk to Freedom, Nelson Mandela

[Applied Intuition @AppliedInt]

You join. You ship. You find what’s broken and fix it.
That’s the bar.

https://t.co/8JzCMa1KTp

[Applied Intuition @AppliedInt]

Come build alongside some of the best engineers in the industry, solving the hardest problems in physical AI.

https://t.co/B0CK0OOJ8w

[John Kim @0xjohnkim]

Every startup says they have the best team. We looked at the data.

@paraformtalent’s Talent Density Index ranks which companies attract, develop and retain the people the market values most.

The latest edition is live.

New Top 50: https://t.co/KoZ5BPpnY8

[Qasar Younis @qasar]

Not 1 but 2 mega announcements to share!

#1: We’re partnering with Honda to build the software platform powering their next-generation of AI-defined vehicles.

https://t.co/6v41Vdv5Mq

[日本経済新聞 電子版（日経電子版） @nikkei]

AI開発の米アプライド、SDVでホンダ・日産と協業　ソフト開発を支援
https://t.co/oivtDbJTO3

[Applied Intuition @AppliedInt]

Silicon Valley software expertise x Japanese engineering excellence.

Applied Intuition and @HondaJP are partnering to speed up Honda’s in-house development of a centralized, upgradeable SDV platform.

Learn more about how we are working together to transform the automotive industry.

https://t.co/5nOqFvFEHG

[Applied Intuition @AppliedInt]

AI-defined vehicles require transforming more than the software in the car, they require transforming how that software gets built.

That’s why we’re excited to partner with @Nissan to support their next-gen SDV and AI-defined vehicle efforts, built on our Vehicle OS.

This is how AI-defined vehicles get built from here.

https://t.co/KoRGIgR4xd

[Applied Intuition @AppliedInt]

Last week, the gearheads at Applied rolled in with some of the rides they've been tinkering on.

[Applied Intuition @AppliedInt]

Our team is headed to @Stanford this Wednesday, October 7th, for the Stanford Computer Forum Career Fair!

Drop by McCaw Hall at the Arrillaga Alumni Center between 11am and 4pm to meet our team and learn about how our team is solving the most complex challenges in physical AI.

https://t.co/PDZsdpKSyR

[Applied Intuition @AppliedInt]

Spotted 👀

[Wei ZHAN @Wei_ZHAN_]

How can we exploit the large-scale in-the-wild dashcam data towards a driving foundation model? Our CVPR 2026 paper shows the power of such “free-gift” unposed and unlabeled data, learning driving representation with strong performance but significantly less labeled data!

[Applied Intuition @AppliedInt]

On NAVSIM, LFG with only 10% of labeled data (81.4 PDMS) already matches other pretrained encoders trained on the full dataset (PPGeo 74.6 PDMS, DINOv3 81.4 PDMS, Pi3 82.8 PDMS). With the full training set LFG reaches 85.2 PDMS, beating multi-camera and lidar systems like UniAD (83.4 PDMS) and Hydra-MDP (84.7 PDMS), using a single front camera.

https://t.co/eVPrBQQbT1

[Applied Intuition @AppliedInt]

Training AVs is complex and expensive to scale in new cities and terrains. From calibrated multi-sensor rigs to millions of labeled miles and painstaking annotation, we need to remove the blockers to autonomy development. Meanwhile, there are millions of hours of unlabeled dashcam footage.
And that’s where LFG comes in with a solution to exploit all this data.

🧵

[Applied Intuition @AppliedInt]

The result:

→ On semantic segmentation, LFG surpasses its own teacher on future frames (0.751 vs 0.680 mIoU), despite predicting blind while the teacher saw the real images.
→ Depth predictions on future frames closely match the teacher (0.31 vs 0.26 AbsRel on KITTI-360, 0.22 vs 0.19 on Waymo Open Dataset).
→ It correctly separates moving objects from static background even when the automated labeling pipeline gets it wrong.