Applied Intuition is the physical AI company bringing intelligence to every moving machine on the planet.
Sunnyvale, CA
- Tweets 1,110
- Following 218
- Followers 6,550
- Likes 382
Applied Intuition retweeted
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!
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.
🧵
3
8
1,523
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.
arxiv.org/abs/2602.22091
167
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.
1
2
348
Architecturally, the model consists of a frozen image encoder backbone paired with trainable causal autoregressive transformers. To reconstruct scenes and generate future predictions, these transformer layers are trained under the guidance of a suite of teacher models for depth, poses, semantic and motion.
1
4
374
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.
🧵
1
2
14
2,421
When you're building a top tier team aimed at solving the most complex problems in physical AI, mediocrity is not an option.
Over the years, @malharhar has interviewed and hired many across Applied. As a high growth company, one of the biggest challenges has been maintaining and evolving the culture at scale.
review.firstround.com/firsth…
1
6
685
Our work with @dstlmod is shaping how the @BritishArmy can effectively deploy swarms of autonomous systems to deliver operational effect.
We led the Disrupter Group, bringing together Rowden, Evolve Dynamics and SAIF Autonomy to deliver this capability Test Bed in just a matter of months.
Learn more about our work: appliedintuition.com/defense…
Working with the @BritishArmy @Bluebearsystems and @AppliedInt we’ve successfully experimented with a collective control drone swarm in a realistic military environment
🔗 gov.uk/government/news/dstl-…
#Dstl #Autonomy #AI
1
1
5
1,224
We're headed to @UCBerkeley tomorrow, September 15th, for the Cal Engineering & Technology Career Fair.
Come by booth #21 to learn more about the physical AI problems we're solving at Applied, from autonomous vehicles and agriculture to trucking, defense, and beyond.
appliedintuition.com/careers…
3
9
1,218
Great code is only half the job. Making it work reliably on physical hardware in the real world is the other half, and it's the part most people don't get to touch.
The ability to drive impact and take ownership has been a big reason why our Deputy CTO, @malharhar, has stayed at Applied all these years. He has been able to go where the problems are.
Read his @firstround write up to learn more about his experience: review.firstround.com/firsth…
1
2
18
1,663
@gaia_no_yoake ドキュメンタリーシリーズの最新エピソードで、いすゞとともに日本の公道でのレベル4自動運転トラックの実現に挑む、舞台裏をご覧ください。
シリコンバレーから日本の高速道路へ。
Applied Intuitionは、安全でスケーラブルな自動運転技術の社会実装を加速させています。
Watch the next episode of @gaia_no_yoake’s documentary series to get a behind-the-scenes look at how we partner with Isuzu to bring Level 4 autonomous trucks to Japan’s public roads—turning our ambitious vision into reality.
From Silicon Valley to Japan’s highways, we're accelerating the deployment of safe, scalable autonomy.
4
9
1,498
At this year’s Agentic AI Summit hosted by @BerkeleyRDI, our Chief Scientist, @Wei_ZHAN_ shared some of the cutting edge research he has been leading in the physical AI space.
As the industry races to deploy L2++ ADAS with imitation-learning-based E2E, Wei tackled a key question: what if end-to-end autonomy could be trained without imitation at all, relying only on reinforcement learning? An idea that runs against the current status quo.
Here are some of his insights
🧵
1
6
31
6,174
40 Engineers.
3 Days.
One mission: bring physical AI to flight.
During our recent hackathon, our defense team accelerated deployment pipelines, ran full HIL/SIL dress rehearsals, and integrated collaborative behaviors to edge compute. Drone software, air combat software, and hardware teams worked side by side to get there.
Want to see your code fly? We're hiring: appliedintuition.com/careers…
2
3
11
1,345
With 1,000+ engineers on our team, it's no surprise the average person at Applied Intuition either comes from a technical background or enjoys teaching themselves technical things.
Join us: appliedintuition.com/careers…
1
9
1,178
Applied Intuition has earned the VIVALDI Inspection Certification from TÜV SÜD, independently verifying our platform for virtual validation of automated driving systems.
Under UNR171, it is not only about proving the AV system works but also proving the simulation tools are trustworthy.
TÜV SÜD evaluated more than 100 requirements across key areas:
🔷 Scenario generation and coverage
🔷 Test management and reporting
🔷 Data integrity and auditability
🔷 Simulation determinism and scalability
Our platform met or exceeded VIVALDI standards across every category.
appliedintuition.com/blog/tu…
2
8
900
Dana for software-defined vehicles brings the speed of AI to development workflows.
We built Dana to reimagine how physical AI applications get developed, including the vehicle software development lifecycle—adding an agentic layer so engineers can build, code, and ship intelligent vehicle features faster and at scale.
appliedintuition.com/blog/fu…
1
4
18
177,550
Most autonomy pretraining still depends on data like lidar scans, HD maps, and hand-annotated trajectories and labels.
Our research team challenged that norm and asked: what if a model learned to drive by watching dashcam footage instead?
LFG, Learning to Drive is a Free Gift, was developed to do just that. The entire system is trained on roughly two million clips from freely available driving videos, spanning varied roads, conditions, and traffic situations. 85.2 PDMS on NAVSIM. One camera. No lidar. No maps.
Read the full breakdown: appliedintuition.com/researc…
4
14
1,473
Dana keeps the flywheel moving and the system learning with every turn.
appliedintuition.com/blog/da…
1
6
9
1,206
Applied Intuition and @aerovironment have announced a strategic teaming agreement to advance uncrewed teaming capabilities for the U.S. military and its allies.
Applied Intuition's Acuity ISR/Strike software will integrate into AV's Mayhem 10™ launched effects system, enabling teams of Mayhem 10 to autonomously find, fix, track, target, and engage targets at the tactical edge — under the supervision of a single operator.
The collaboration supports the U.S. Army's Launched Effects program and is designed to scale across short, medium, and long range requirements.
appliedintuition.com/press-r…
3
16
2,159
“Twenty years from now, we won't remember which company had the best world model in 2027. We'll remember which company figured out how to continuously turn intelligence into deployed systems. That’s the problem we've been working on.”
Our co-founder and CTO, Peter Ludwig, shares his thoughts on what the future of physical AI will look like when the goal is to make more than a billion machines intelligent.
.@AppliedInt Co-founder and CTO Peter Ludwig says "a billion machines will become autonomous or intelligent over the next ten years."
"Cars, trucks, tractors, mining haulers, defense systems, warehouse robots, humanoids—the physical economy will be rebuilt around software that perceives, decides, and acts."
"The prevailing assumption about how we get there goes something like this: models keep improving, world models mature, foundation models for robotics arrive, and autonomy falls out the other end. Intelligence is the whole game; scale the intelligence and the machines will follow."
"The contrarian bet, then, isn't against intelligence. It's that the next order of magnitude in physical AI comes from making the engineering system as intelligent as the models it carries."
Full piece on compounding systems and Applied Intuition's newest platform, Dana: a16z.news/p/the-next-ai-moat…
2
4
22
8,498