Nolan Fey

Robotics PhD Student @ MIT

[Nolan Fey @nolan_fey]

Excited to share my recent work with @gabe_mrgl , Martin Pettico, and @pulkitology . We’re pushing the limits of whole-body control to make robots faster, stronger, and more athletic!

[Adam Wei @adamwei_]

🤖 We introduce Ambient Diffusion Policy, a simple and principled method for training policies with suboptimal data in robotics.

Suboptimal data is everywhere in robotics…
❌ Data filtering is wasteful
❌ Co-training learns both good and bad features
✅ Ambient Diffusion Policy selectively learns useful features via noise-dependent data usage

👇🧵(1/5)

[Nolan Fey @nolan_fey]

Thank you for including UAN!

[Guanya Shi @GuanyaShi]

It was a great pleasure to give a guest lecture, "Sim2Real Robot Learning: A Holistic Overview," for @chelseabfinn's CS224R at @Stanford. The lecture covered the motivation, history, key methods, and future outlook of sim-to-real robot learning. Slides: https://t.co/NZRk1WvQOX

[Pulkit Agrawal @pulkitology]

Eka means unity -- “one,” in Sanskrit and “first” in Finnish.

We’re building intelligence for the physical world in its native language: forces.

Until now, robotics faced a tradeoff — generality or speed. The real world requires both. Robotics also faced a data problem.

Our Vision–Force–Action (VFA) model — the first of its kind — breaks the generality-speed tradeoff and the data barrier.

It's a new foundation uniting performance, generality, and safety for putting capable robots in everyone's hands.

Today, I am excited to share our journey of pushing robots beyond human limits.

Today, dexterity becomes scalable.

Today, I welcome you to the Era of Eka.

Co-founded with @haarnoja, and so thrilled and grateful to be working with a dream team at @EkaRobotics.

Learn more: https://t.co/QYQ6x2Etyi

[Younghyo Park @younghyo_park]

What's different between these two BC policies? It's the same architecture, training budget, and data collection setup — the only difference is the controller gains!

Controller gains are an understudied design parameter in robot learning. In our new work (w/ @BronarsToni*, @pulkitology), we show how they act as an inductive bias across BC, RL, and Sim2Real transfer, with real consequences on performance. Here's what we found 🧵

* Equal Contribution
📄arxiv: https://t.co/SMYgh7i8cA
🔗website: https://t.co/cLCd1FYCdJ

[Nolan Fey @nolan_fey]

Compliance is critical not only for safety but also human-like object interaction. Hope to see more of the sim2real RL community explore compliant control. Great working with @gabe_mrgl, @michl_wang, and @pulkitology.

[Gabe Margolis @gabe_mrgl]

Excited to share SoftMimic -- a new approach for learning compliant humanoid policies that interact gently with the world.

[Carlo Sferrazza @carlo_sferrazza]

Excited to share that I'll be joining @UTAustin in Fall 2026 as an Assistant Professor with @utmechengr @texas_robotics!
I'm looking for PhD students interested in humanoids, dexterous manipulation, tactile sensing, and robot learning in general -- consider applying this cycle!

[Jyo Pari @jyo_pari]

For agents to improve over time, they can’t afford to forget what they’ve already mastered.

We found that supervised fine-tuning forgets more than RL when training on a new task!

Want to find out why? 👇

[Martin Peticco @martinpeticco]

What’s keeping robot arms from working like human arms?

They're big, slow, have the wrong joints, and can't conform to their environment. DexWrist solves all of these issues and simplifies learning constrained, dynamic manipulation👉 https://t.co/qxNJVVx5hV

[Gabe Margolis @gabe_mrgl]

Catch @nolan_fey's oral/poster at today's ICLR Robot Learning Workshop!

https://t.co/NqEe1eca0k

The paper will also appear at RSS.

[idan shenfeld @IdanShenfeld]

The next frontier for AI shouldn’t just be generally helpful.

It should be helpful for you!

Our new paper shows how to personalize LLMs — efficiently, scalably, and without retraining.

Meet PReF (https://t.co/XaLZAwimse)
1\n

[Nolan Fey @nolan_fey]

@haitong__wang @gabe_mrgl @pulkitology Thanks! The actuators lack output torque sensors, so we don't have "labels" for supervised learning

[Nolan Fey @nolan_fey]

Excited to share my recent work with @gabe_mrgl , Martin Pettico, and @pulkitology . We’re pushing the limits of whole-body control to make robots faster, stronger, and more athletic!

[Pulkit Agrawal @pulkitology]

You aren't doing robotics if you are not breaking some robots! https://t.co/mBSVYicuBg

[Nolan Fey @nolan_fey]

@AayushDesh @gabe_mrgl @pulkitology Thanks! I've been working on whole-body control for about a year and a half now. Project timelines can vary a lot though depending on experience level and how much past work you can leverage

[Nolan Fey @nolan_fey]

@albericlajarte @gabe_mrgl @pulkitology Thanks! -- It takes in a history of past (simulated) position errors and velocity measurements. We use the hardware data for the reward function and to set the initial state of the sim during UAN training.

[Pulkit Agrawal @pulkitology]

Presenting Unsupervised Actuator Nets (UANs) that push the limits of agile whole-body control without the need for reward shaping!

⚡️ UANs reduce the sim2real gap in robot's motors removing the need for reward design to bridge the sim2real gap.

⚡️ A pre-trained whole-body controller uses reference motion as a hint to maximize task performance!

Learn more: https://t.co/f68scKkU8Z

Work led by @nolan_fey , @gabe_mrgl in collaboration with Martin.

[Nolan Fey @nolan_fey]

@yacineMTB @ChongZitaZhang Valid option but then the robot won’t throw as far, so we mechanically reinforced the arm instead

[Nolan Fey @nolan_fey]

Check out our website for more details: https://t.co/hExlhDaiHH

[Nolan Fey @nolan_fey]

To address exploration challenges, we fine-tune a foundational whole-body controller with simple task rewards, using reference trajectories as helpful hints.