Dhruv Diddi

Physical AI Specialization | Solo Tech | Nebius Fellow | UFB Champion | IEEE Humanoids | Formerly at Google AR/VR, Turo, YouTube

[Dhruv Diddi @DhruvDiddi]

Today I assembled the first batch of reBot DevArm in the U.S!

First one on the planet! 🇺🇸⚙️

But this isn’t about a robot arm.

This is about what happens when open source hits robotics.

For years:
•Hardware was locked
•Robotics was expensive
•Embodied AI was out of reach

Now?

Anyone can get their hands on:
•6 DOF manipulation
•Real precision (<0.2 mm repeatability)
•Full stack access (ROS, Isaac Sim, LeRobot)

This is how movements start.

Not in labs.
Not behind paywalls.
But in the hands of builders.

Massive respect to @seeedstudio for pushing true open-source robotics forward!

We’re about to see:
→ Thousands of robot arms trained like athletes
→ Real-world datasets explode
→ Physical AI built in garages, not just research labs

At @Solo__Tech , this is the unlock we’ve been waiting for, training and deploying Physical AI skill models on real hardware, anywhere.

No sims. No vaporware. No excuses.

Production Grade Physical AI.

Want to get access? Check out the Physical AI Gym in San Francisco or DM me.

[DailyPapers @HuggingPapers]

NVIDIA just released a finetuned GR00T N1.7 robot policy on Hugging Face

Trained on the LIBERO benchmark for Panda arm manipulation

Ready to deploy via LeRobot

[Dhruv Diddi @DhruvDiddi]

@stevencheng Like a hub?

[Jia-Bin Huang @jbhuang0604]

POV: me starting to learn robotics

[Frontier Tower @frontiertower]

Meet your new Robotics Community Lead: @DhruvDiddi
Dhruv is an ML engineer, founder, and Meta Llama Impact Grant recipient who's been quietly building something remarkable — right here at Frontier Tower.

Through Solo Tech, he's advancing Physical AI Inference: offline, multilingual AI tools designed to reach the people most technology leaves behind, across agriculture, education, and health in underserved rural communities.

That's the kind of work that defines the frontier

We couldn't be more excited to have him stepping into this role, and we know he's going to bring that same energy and vision to the Robotics community here.
Explore his work at https://t.co/6BxuzGFBKO.

[Sujee Maniyam @sujee_dev]

@nebiusai booths are never boring.

Meet NEBU - our Nebius pup 🐶- making a new friend 🐉

Stop by the Nebius booth at the @aiDotEngineer conf.

You can play with the robots... and chat with the humans, too. 😄

@nebiustf @demian_ai @DhruvDiddi

[Jim Fan @DrJimFan]

ENPIRE -&gt; ASPIRE, our 2nd work in the series for Physical AutoResearch. We are building the components for robot self-improvement, one /skill at a time.

[Dhruv Diddi @DhruvDiddi]

@DrJimFan Wow! This is simple inspiring work @DrJimFan 🦾🦾💯💯⚡️⚡️

[Jim Fan @DrJimFan]

Today, we give robots a /skills library that self-evolves and compounds indefinitely! Introducing ASPIRE: a robot solving its 100th task is no longer as clueless as solving its first. Coding agents observe multimodal sensory traces from simulation and real robots, launch an evolutionary search over control programs, and distill the best know-how into an ever-expanding library.

ASPIRE is a new type of continual learning: "training" is skill refinement instead of gradient descent.
"Trained model" is a repo of sensorimotor skills instead of floating weights.
“Distributed training” is a panel of agents each practicing a different skill instead of sharded minibatches.

Here's the beauty: ASPIRE gives the tired terms "sim2real transfer" and "cross-embodiment transfer" a whole new meaning. Bridging the sim-to-real gap is notoriously brutal. An end-to-end policy has to swallow both the visual shift (sim looks toyish next to a real camera) and the subtle contact physics it never quite gets right. ASPIRE sidesteps the mess, because it doesn't ship pixels or weights across the gap, but ships the know-how. The robot still has to practice in the real world, not zero-shot, but it gets there way faster because it isn't rediscovering the strategy from scratch. Same for going single-arm to bimanual hardware, which usually requires new data and retraining from zero. ASPIRE achieves up to ~10x cut in "transfer learning” tokens (yes, tokens are the new unit of *training* compute ;)

Check out our gallery of 150+ tasks and 90+ skills the robots taught themselves, all on the website! Kind of wild that we can ship the "learned weights" as an HTML page rather than a GGUF. We'll open-source the full stack so your own robot library starts compounding from ours!

Deep dive in thread:

[Alexandr Wang @alexandr_wang]

some exciting new work from our AI teams at Meta on non-invasive brain computer interfaces!

[AGIBOT @AGIBOTofficial]

Today, AGIBOT's 15,000th robot officially rolled off the production line, marking another step toward scaled production and real-world deployment.

The numbers tell two achievements: a growing product portfolio and an accelerating path to scaled deployment.
📈 0 → 1,000 robots: 2 years of product validation
📈 1,000 → 5,000 robots: 1 year to batch delivery
📈 5,000 → 10,000 robots: 3 months to large-scale deployment
📈 10,000 → 15,000 robots: another 3 months to accelerate real-world deployment at scale

15,000 robots is more than a production milestone. It reflects the embodied AI industry's transition from building robots to deploying them at scale.

#AGIBOT #EmbodiedAI #HumanoidRobots #Robotics #MassProduction

[a16z @a16z]

VC interest in robotics is surging

Charts of the Week: https://t.co/qmjdkZzisp

[Dhruv Diddi @DhruvDiddi]

@Abhindas1 @the_varunrana @cluely @UseCorgi @LinkedIn Connected to @the_varunrana on LinkedIn, down to do a collab with robots 🦾😊

[Dhruv Diddi @DhruvDiddi]

@Abhindas1 @the_varunrana @cluely @UseCorgi @LinkedIn Hahahah no

[Dhruv Diddi @DhruvDiddi]

@JacklouisP Insightful! 💯

[BitRobot 🦾 @BitRobotNetwork]

1/ Introducing HIW-500 (Humanoids-in-the-Wild 500):
the largest open-source humanoid teleop dataset collected in real homes

Built w/ @UnitreeRobotics @huggingface across 12 homes in Southeast Asia, it covers:
&gt; 500+ hrs
&gt; 23K+ episodes
&gt; 10+ TB
&gt; 10+ household tasks

[Lester Li @sizhe_lester_li]

Robot learning is moving beyond policies built for one robot, one scene, one task.

At MIT, we’re exploring a different path: turning video world models into embodiment-agnostic robot policies.

Introducing VERA: a 14B video-to-action system that controls robots across embodiments, skills, and environments.

From zero-shot pick-and-place on a real Panda arm to contact-rich cube reorientation with a 16-DoF robotic hand.

Different robots. Different environments. Different tasks.
Same video planner. Same weights.

We’re open-sourcing everything so you can fine-tune VERA for your own robot setup too. Deep dive in the thread:

🔗 https://t.co/hzuYZ2m5lS
🧵 (1/7)

[Dhruv Diddi @DhruvDiddi]

@quantbagel @RoboticsCtr got you! 🦾

[Dhruv Diddi @DhruvDiddi]

@michellelsun @UnitreeRobotics Insightful!!!

[Brad Porter @BradPorter_]

Today we introduce Proxie Gen2 to the world.

At Cobot we have set out to build something that didn't exist: a robot that moves through real environments and manipulates real objects, autonomously, alongside real people.

That's compounding advantage. More on our vision here https://t.co/oUlmpkvwKn

[AGIBOT @AGIBOTofficial]

Day 1 is live: Watch multiple AGIBOT G2 humanoid robots working on a real tablet production line.

This is autonomous robot operation inside an active factory workflow — not a simulation or staged demo.

Livestream link:
⏰8:00 AM-12:00 PM (UTC+8)：https://t.co/EKdXpawgeN
⏰1:00 PM-7:00 PM (UTC+8)：https://t.co/qUdK19cV2F