Pinned Tweet
There’s a discussion going on rn about two recent robotic reward models: TOPReward⛰️ and Robometer🌡️
Which one is better? It depends entirely on your objective!
Here is a deep dive into the conceptual differences, strengths, and weaknesses of both. 🧵👇
Marius Memmel retweeted
Can and should a general-purpose model serve as a robot policy?
In Astranomy, we study GPT-6 Astra for general pick-and-place manipulation. Astra sets a new SOTA on RoboLab-120, but real-time robot control remains an open challenge.
Full tech report:
research.nvidia.com/labs/srl…
Marius Memmel retweeted
What to remember in the past to act—spatial, temporal or motion details?
We often assume what’s useful, but that’s hard to know in advance.
Meet IMPRINT 🧠: retain rich memory first, then learn to use it for control. Compact latents keep inference fast as history grows. 🧵 1/10
Marius Memmel retweeted
(1/6) From @GoogleDeepmind’s AlphaGo to AlphaZero, we saw machines find moves that reached beyond what we’d imagined for them. No one taught them those strategies. They emerged from reinforcement learning: playing, failing, and trying again under a single binary task reward for success or failure. Inspired by them, we couldn’t help but wonder: what might a robot discover if we gave it that same freedom to learn?
That question led us to AlphaNIST. Starting tabula rasa, with that same binary reward plus only a simple control cost, a single policy solves all 20 @NIST assembly tasks at a 98.2% success rate in simulation. More surprising still, AlphaNIST can complete 10 different tasks in a row, receiving that reward only once, after all 10 are done.
Just as AlphaGo’s strategies surprised its creators, AlphaNIST discovered dexterous strategies we couldn’t have come up with ourselves.
Paper: arxiv.org/abs/2610.13354
Website: alpha-nist.github.io
GPT-6 Astra unlocks a whole new level of simulation scaling! It generates diverse environments, designs and solves tasks, and deploys seamlessly across embodiments.
Below: 25 unique environments, 25 multi-step tasks, and 5 robot embodiments generated in under 24 hours with just 3 generic prompts!
🧵
Huge thanks to @kevin_zakka and collaborators for developing MuJoCo Menagerie [3], and to @seohong_park for key insights on generating human-like demonstration data [4]!
References:
[1] arxiv.org/abs/2602.11337
[2] arxiv.org/abs/2603.04356
[3] github.com/google-deepmind/m…
[4] seohong.me/blog/behavioral-c…
Marius Memmel retweeted
🚀 Looking for a reliable Franka controller with seamless sim-to-real transfer?
Meet FrankaTwin: github.com/tsrobcvai/frankat…
🎮 Joint/Cartesian position & impedance + gripper
🎯 System ID: 3.6 mm EE / 28 mrad joint RMSE (sim vs. real)
Remember URDFormer? The vision was simple: image in, URDF out.
Fast-forward 2.5 years, and GPT-6 Astra can solve this task zero-shot.
This is a massive win for the community: a scalable and cheap way to generate high-quality simulation assets!
The crazy part? This worked on the very first try with the dumbest prompt I could come up with:
"You are a robotics engineer. Convert the scene shown in the image a single valid URDF description."
GPT-6 Astra (Max)
While the original URDFormer architecture is now obsolete, the premise has aged like fine wine 🍷
urdformer.github.io/
@ZoeyC17 @aaronwalsman @abhishekunique7
Marius Memmel retweeted
We are giving out $500k and free YAM arms to academic teams to design dexterous manipulation benchmarks and run real-world evaluations.
General-purpose robots could soon be in homes and data centers. Society should know what robots can do before they get there.
ALT Dark teal gradient with white text. Small label "Expression of Interest" above the headline "Call for Open-Source Robotics Benchmarks" and the line "We are funding academic teams to design open-source robotics benchmarks for dexterous manipulation and to run real-world evaluations."
Update the high-level VLM while keeping the low-level policy fixed. Then run RL on offline data to avoid expensive environment interactions. Clever idea!
How should robots think? 🤔
In our new paper R³, we introduce a simple way to get robots to think before they act—like humans: free-form, deliberate, and actually useful.
The recipe is surprisingly simple: just RL, done carefully. Yet it enables reasoning that can effectively steer low-level robot policies.
🧵[0/9]
I recently tried out their github repo on some random mujoco environment and was blown away by how well a zero-shot VLM could already solve the task.
No policy, no fancy action head, just outputting joint positions or endeffector actions! Highly recommend checking it out :)
Introducing @robocurve, a Public Benefit Corporation to measure and report frontier robotics capabilities.
We build real-world evaluations for robots and publish results as a neutral third party.
Marius Memmel retweeted
We released DROID+, a new and improved DROID control stack from SRL. We believe robots (and hardware) should be easy to setup and easy to use, and so we updated the DROID stack to be the same. @HugoHadfield1
github.com/nvlabs/droidplus
Here's pi0.5 doing our "hello world" task:
When we were exploring trajectory retrieval, we were hoping that some day in-context learning would be unlocked for robotics.
Turns out all it took was two years and tons and tons of data.
Congrats @GeneralistAI on the impressive demo!
Check out our past work on retrieval: weirdlabuw.github.io/strap/ 🎒
