←
Stephen James588 posts
Stephen James avatar

Stephen James

@stepjamUK

CEO @Neuracore_AI | Assistant Professor @imperialcollege | ex-Director of Dyson Robot Learning Lab | Postdoc @UCBerkeley w/ @pabbeel | PhD ICL w/ @ajdDavison

◷ Joined January 2010▧ 217 Photos and videos
Stephen James avatar
Stephen James@stepjamUK·24 Sep 2025

𝗔𝗳𝘁𝗲𝗿 𝟭𝟬+ 𝘆𝗲𝗮𝗿𝘀 𝗶𝗻 𝗿𝗼𝗯𝗼𝘁 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴, from my PhD at Imperial to Berkeley to building the Dyson Robot Learning Lab, one frustration kept hitting me: 𝗪𝗵𝘆 𝗱𝗼 𝗜 𝗵𝗮𝘃𝗲 𝘁𝗼 𝗿𝗲𝗯𝘂𝗶𝗹𝗱 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲 𝗶𝗻𝗳𝗿𝗮𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲 𝗼𝘃𝗲𝗿 𝗮𝗻𝗱 𝗼𝘃𝗲𝗿 𝗮𝗴𝗮𝗶𝗻? 𝗧𝗵𝗲 𝗽𝗮𝘁𝘁𝗲𝗿𝗻 𝗜 𝗸𝗲𝗽𝘁 𝘀𝗲𝗲𝗶𝗻𝗴: • New robotics team starts • Spends 6 months building data collection pipeline • Spends another 3 months debugging synchronization issues • Finally starts collecting task-specific data • Realizes their infrastructure choices limit their flexibility • Starts over 𝗧𝗵𝗶𝘀 𝗶𝘀 𝘁𝗵𝗲 𝘄𝗵𝗼𝗹𝗲 𝗽𝗼𝗶𝗻𝘁 𝗼𝗳 𝗿𝗼𝗯𝗼𝘁 𝗹𝗲𝗮𝗿𝗻𝗶𝗻𝗴: Robot learning is fundamentally data-driven. Whether you're picking strawberries or assembling electronics, the core infrastructure needs are identical. That's actually why I was so interested in pursuing data-driven robotics over a decade ago. 𝗬𝗼𝘂 𝗮𝗹𝘄𝗮𝘆𝘀 𝗻𝗲𝗲𝗱: • Multi-sensor data synchronization across different frequencies • Flexible storage that works with future algorithms • Visualization tools to understand your data • The ability to experiment with different temporal resolutions • Robust logging that captures everything you might need later The trend towards AI in robotics is growing, with robots needing to process and analyze large amounts of sensor data to manage variability and unpredictability in real environments. 𝗕𝘂𝘁 𝗲𝘃𝗲𝗿𝘆 𝘁𝗲𝗮𝗺 𝗯𝘂𝗶𝗹𝗱𝘀 𝘁𝗵𝗶𝘀 𝗳𝗿𝗼𝗺 𝘀𝗰𝗿𝗮𝘁𝗰𝗵. Imagine if every web developer had to build their own database, web server, and deployment pipeline before writing their first line of application code. 𝗧𝗵𝗶𝘀 𝗶𝘀 𝘄𝗵𝘆 𝗜 𝗳𝗼𝘂𝗻𝗱𝗲𝗱 𝗡𝗲𝘂𝗿𝗮𝗰𝗼𝗿𝗲. Instead of every robotics team spending months on infrastructure, we provide the common tools that let you go from "I have a robot" to "I'm shipping intelligent robot behaviors" in days, not months. 𝗧𝗵𝗲 𝗿𝗲𝗮𝗹 𝗶𝗻𝗻𝗼𝘃𝗮𝘁𝗶𝗼𝗻 𝗶𝗻 𝗿𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝘄𝗼𝗻'𝘁 𝗰𝗼𝗺𝗲 𝗳𝗿𝗼𝗺 𝗲𝘃𝗲𝗿𝘆𝗼𝗻𝗲 𝗿𝗲𝗯𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲 𝗽𝗹𝘂𝗺𝗯𝗶𝗻𝗴. 𝗜𝘁'𝗹𝗹 𝗰𝗼𝗺𝗲 𝗳𝗿𝗼𝗺 𝘁𝗲𝗮𝗺𝘀 𝘄𝗵𝗼 𝗰𝗮𝗻 𝗳𝗼𝗰𝘂𝘀 𝗲𝗻𝘁𝗶𝗿𝗲𝗹𝘆 𝗼𝗻 𝘄𝗵𝗮𝘁 𝗺𝗮𝗸𝗲𝘀 𝘁𝗵𝗲𝗶𝗿 𝗮𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻 𝘂𝗻𝗶𝗾𝘂𝗲. Robot learning shouldn't be bottlenecked by infrastructure. It should be bottlenecked by creativity. What's the longest you've spent building infrastructure before getting to the actual robotics problem you wanted to solve?

0:10
Stephen James avatar
Stephen James@stepjamUK·5h

Faster iteration is everything in robot learning. That’s why I’m excited about Policy Playback, the latest feature from the Neuracore team. It lets you preview what your policy is predicting while training is still running, so you can fix issues early and save time and compute.

Waiting for a training run to finish just to see if your policy works? There’s now a faster way. Policy Playback on Neuracore lets you watch your policy’s predicted actions while training is still running. Catch problems early, check your data as you go, and stop wasting time and compute on runs that are off track. Try it out below!

0:18
Stephen James avatar
Stephen James@stepjamUK·Nov 17

A great example of what's possible when you bring the entire robotics workflow together on one platform. Always exciting to see what teams can achieve with the right tools on @Neuracore_AI.

Here a @Universal_Robot (UR5) arm threads a cable through a car door, running fully autonomously. From collecting demonstrations to training and deployment, the entire process was completed on Neuracore.

0:27
Stephen James avatar
Stephen James@stepjamUK·Nov 17

Putting a 552B mixture-of-experts backbone under a VLA mostly pays off when demos are scarce. On LIBERO-Goal, 10 demos per task beats a 2B backbone trained on 50 (87.8% vs 85.6%), though the gap closes by 50 demos. The cost side is worth noting too: 216 ms per action chunk, but on four H200s. Cool work by Zekun Qi, He Wang, Yi Li and the team at @Tsinghua_Uni, @PKU1898, @sjtu1896 and @GalbotRobotics. Paper: arxiv.org/abs/2611.21607 Project page: galaxygeneralrobotics.github…

0:43
Neuracore avatar
⟳ Stephen James retweeted
Neuracore@Neuracore_AI·Nov 16

One platform. An entire ecosystem. From data collection, visualisation and curation to deployment, Neuracore makes it easier than ever to go from demo to a deployed policy. Find out how you can get your hardware running a trained policy in just one hour. Link in the comments.

0:27
Neuracore avatar
⟳ Stephen James retweeted
Neuracore@Neuracore_AI·Nov 13

Spotting issues in your data collection pipeline has never been easier with Neuracore's Trace Viewer. Find out how the team used it to train an autonomous policy in just one hour. Full breakdown in the comments below ⬇️

0:07
Stephen James avatar
Stephen James@stepjamUK·Nov 12

One hour from first demo to autonomous policy, live at #ROSCon UK. This is what robot learning should feel like: deploying in hours, not days, with your team focused on the task at hand.

We trained an autonomous robot policy in just one hour at #ROSConUK 2026! At ROSCon, Mark Naeem and Damon Hayhurst collected demonstrations live on our stand, trained a policy using Neuracore and deployed it straight back onto the OpenArm. Watch how we used Neuracore to teach the robot to perform the task autonomously, all within the hour. #ROSCon2026 #RobotLearning #PhysicalAI

1:19
Stephen James avatar
Stephen James@stepjamUK·Nov 12

Our @Universal_Robot UR5 threading a cable through a car door. Fully autonomous, running an ACT policy. Cable is the task I’d judge any manipulation policy on. Rigid parts let a robot memorise a motion. Cable moves every time you touch it, so the policy has to actually watch what it’s doing. Collected, trained and deployed on @Neuracore_AI. Full video in the comments.

0:14
Stephen James avatar
Stephen James@stepjamUK·Nov 10

A popular VLA training recipe blocks the action expert from updating the VLM underneath it. A new paper asks whether that should be the default. Asher Hancock, Marco Pavone and the team at @nvidia, Princeton University and Stanford University varied two things independently: whether the VLM also predicts discrete action tokens, and whether the expert’s gradients flow back into it. With action tokens on, blocking the gradients costs little in open-loop driving. With them off, letting the gradients through cuts trajectory error by about 25%. Closed loop is where it gets interesting. Trained together from the start, letting the gradients through lifted driving route progress from 0.600 to 0.703, even with action tokens on. In manipulation, a π0.5 re-implementation went from 10.3% to 32.9% task progress without FAST, and from 19.5% to 30.7% with it. MolmoAct2 moved the same direction, though the gain with FAST was small (22.0% to 24.3%). One training run per condition, and all the closed-loop results are in simulation. I’d read it as a good reason to question insulation as the default, not proof it’s wrong. Paper: arxiv.org/abs/2611.05249 Project page: mot-vla-gradient-routing.git…

0:16
Stephen James avatar
Stephen James@stepjamUK·Nov 5

Wrist cameras give robots great close-ups, but they’re stuck to the hand. FoveaVLA asks whether the policy can just choose where to look instead. @bingao_chen, Karen Liu, Guy Tevet and the team at @Stanford and @Princeton built it on π0.5. With every action chunk, the model also predicts the box it will need to see next and crops it from the full-resolution external image. Squashing a 1280x720 frame to 224x224 blurs the gripper and the object, and the crop gives that detail back. One external camera plus depth, no wrist camera: 34 of 48 real-world trials (70.8%), against 25 of 48 (52.1%) for wrist-equipped π0.5. Retrain π0.5 on the external view alone and it falls to 6.3%. It’s a small eval, 12 trials per suite, so I’d like to see more. The ablation is the part that convinces me, though. Crop alone gets 20.8%, depth alone 6.3%, both together 70.8%. Code and models are open and can be found below: Paper: lnkd.in/egBJndZF Project page: lnkd.in/evwNNUbf

0:49
Stephen James avatar
Stephen James@stepjamUK·Nov 4

The @Neuracore_AI team will be running live demos at @ABBRobotics upcoming event on the 2nd of December. Come and join us and see what’s ready to deploy on the robots you already run.

Will you be at @ABBRobotics PoWa of Collaboration event in Milton Keynes on 2 December? The Neuracore team will be there. Come and say hello. We’ll be talking about how teams go from collecting demonstrations on the cobots they already run to deploying trained skills. Neuracore is the robot skill creation engine that makes in-house physical AI possible. Collect, visualise, train and deploy, on ABB, FANUC, Universal Robots and more. Want dedicated time with us on the day? Get in touch and we’ll find a slot at the event: neuracore.com/ Event details and registration: campaign.abbrobotics.com/l/1…

Post attachment
Stephen James avatar
Stephen James@stepjamUK·Nov 3

Good data starts with good visibility. Trace Viewer makes it easier to understand what's happening during data collection, spot issues early and know exactly what you're feeding into training. Another step towards making robot learning workflows more reliable.

New in Neuracore: Trace Viewer shows every time you log data and highlights issues in your data collection pipeline. Review your raw data before synchronisation, giving you full visibility into what's being collected and allowing you to catch problems early. Know exactly what's going into training, so you can get the most out of every dataset.

0:13
Stephen James avatar
Stephen James@stepjamUK·Nov 3

𝗘𝘃𝗲𝗿𝘆 𝗳𝗲𝘄 𝗺𝗼𝗻𝘁𝗵𝘀 𝘀𝗼𝗺𝗲𝗼𝗻𝗲 𝗽𝗼𝘀𝘁𝘀 𝘁𝗵𝗮𝘁 𝗨𝗞 𝗿𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝘁𝗮𝗹𝗲𝗻𝘁 𝗶𝘀 𝗹𝗲𝗮𝘃𝗶𝗻𝗴 𝗳𝗼𝗿 𝘁𝗵𝗲 𝗩𝗮𝗹𝗹𝗲𝘆. I did my postdoc at Berkeley and came back to London. Turns out I’m not the only one. The @Neuracore_AI team just spent three days at ROSCon UK in Edinburgh, and I think it’s time to retire that post. The question we heard most at our stand wasn’t about the product. It was some version of “can I come and work with you?” Robot learning engineers, PhD students finishing up, people already shipping robots for other companies. The talent is here. And people want to build here. Three things the brain drain story gets wrong: 1. 𝗧𝗵𝗲 𝗱𝗶𝗿𝗲𝗰𝘁𝗶𝗼𝗻 𝗼𝗳 𝘁𝗿𝗮𝘃𝗲𝗹 𝗶𝘀 𝗰𝗵𝗮𝗻𝗴𝗶𝗻𝗴. More tech workers are now moving from the US to Europe than the other way, and the UK is one of the biggest gainers. The room in Edinburgh reflected it: 240 people, 42 companies, 21 universities, half industry, half academia. 2. 𝗧𝗵𝗲 𝗺𝗼𝗻𝗲𝘆 𝗶𝘀 𝘀𝘁𝗮𝗿𝘁𝗶𝗻𝗴 𝘁𝗼 𝗳𝗼𝗹𝗹𝗼𝘄. UK robotics companies raised $258m by August 2026, already exceeding the total raised across all of 2025. That’s a market worth paying attention to. 3. 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗶𝘀 𝘀𝘁𝗮𝗿𝘁𝗶𝗻𝗴 𝘁𝗼 𝗺𝗼𝘃𝗲 𝗰𝗹𝗼𝘀𝗲𝗿 𝘁𝗼 𝗿𝗲𝗮𝗹-𝘄𝗼𝗿𝗹𝗱 𝗱𝗲𝗽𝗹𝗼𝘆𝗺𝗲𝗻𝘁. Advanced Research + Invention Agency (ARIA)’s Robot Dexterity programme is backing 26 teams working across robotics hardware, manipulation and control. Its focus is increasingly on turning research breakthroughs into systems that work in the real world. So the question isn’t whether the UK has the people. It’s whether we give them the tools to ship. #ROSCon #RobotLearning #UKRobotics

Post attachment
Neuracore avatar
⟳ Stephen James retweeted
Neuracore@Neuracore_AI·Oct 29

OpenArm 1.0 cleans up a spill with Neuracore fully autonomous. Neuracore streams camera feeds and joint states in real time, turning robot demonstrations into datasets used to train policies for autonomous execution. See what you can do with Neuracore. Link in the comments. #Robotics #RobotLearning #OpenArm #PhysicalAI

0:32