
wooo
Replying to @claudeai
Fable 5.2 shows substantially improved skills in controlling physical robots, even on tasks it has never explicitly been trained to do.
On RoboDojo, a benchmark with a simulated two-arm robot, it outperformed other models and most AI systems built to control robots.
dave @ CoRL 2026 retweeted
Can one world model handle rigid boxes, plush toys, and cloth?
Introducing MoRE: a Mixture-of-Experts 3D world model that predicts how objects move across materials and plans real-robot actions with MPC.
See us at #CoRL2026: Monday, Spotlight Session 2 & Poster Session 1 🤠!
Heading to Austin for #CoRL2026 ✈️ Excited to meet up with old and new friends! 🤠
Come check out our EgoWAM poster and talk with us:
📍 Poster Session 2, #62 · JW Marriott, Lone Star (3rd floor)
🕔 Tue, Nov 10 · 5:00–6:30 PM
Also excited to chat about world (action) models, cross-embodiment learning, agentic robotics, software-hardware co-design, and anything else about robot learning during the conference. DMs open, come say hi! 👋
dave @ CoRL 2026 retweeted
What should transfer from a human video to a robot?
Human2Any learns how objects interact, then adapts that knowledge through test-time reasoning and planning.
Accepted to #CoRL2026! I'll be presenting in person next week—come say hi!
human2any.github.io (1/n)
dave @ CoRL 2026 retweeted
In sim-and-real co-training, robots learn from a few real demos plus ample sim data. But which sim data should we generate?
MetaGenSim meta-learns what to simulate: 2.5× the real-world success of uniform sim data, matching expert hand-tuning.
meta-gensim.github.io
#CoRL2026
dave @ CoRL 2026 retweeted
Can collecting robot data be as easy as 𝗽𝗿𝗲𝘀𝘀𝗶𝗻𝗴 𝗿𝗲𝗰𝗼𝗿𝗱?
Introducing UMI-Live, a 𝗰𝗼𝗺𝗽𝗹𝗲𝘁𝗲𝗹𝘆 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 bimanual UMI we made that takes you from handheld demonstrations all the way to a trained robot policy.
It's built to be easy to use. Each gripper has its own camera, LiDAR, compute, and battery, so there are no base stations to mount and nothing to calibrate in the scene. You press one button and both hands start recording.
While you keep collecting, our pipeline processes finished episodes in parallel and turns them into LeRobot datasets, automatically uploaded on Huggingface. VLAs fine-tuned mostly on this data succeed in 𝟭𝟬/𝟭𝟬 (π0.5) and 𝟴/𝟭𝟬 (MolmoAct2) trials on a real bimanual task.
We're open-sourcing everything, from the hardware designs and build guides to the code and ~40 hours of data 🧵
im so curious what the API interface for this looks like 👀
is it TCP or UDP? push or pull? how are execution horizons configured?
Announcing the beta release of the Pi API. We’ve partnered with companies across diverse industries to adapt our models to their robots and applications, from harvesting strawberries to assembling servers. Now we’re opening access to more teams.
2
180
shower thought: one day it may be more eco-friendly to do your taxes with datacenter AI than to actually do it yourself
1
2
184
so many custom inference engines nowadays, how many are actually running in production? outside of the labs, I would imagine most are just running a vllm/sglang fork?
1
2
235
dave @ CoRL 2026 retweeted
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
dave @ CoRL 2026 retweeted
happy to share that Armory will be presented at #CoRL2026. See you all in Austin in November! Both @davidhe137 and I will be there, reach out if you would like to chat!🦾
btw, cool walkthrough video we took of a “lego sorting factory” in action: 14 robots scheduled onto 1 cloud GPU at 30hz with train-time RTC!
🤖 Scaling deployment in robotics can be difficult and expensive. How can we properly serve a VLA/WAM to 10+ robots concurrently from a single GPU?
Introducing Armory, a system for serving large robot policies to a fleet of robots from the cloud/edge. Through real-time scheduling of action chunks, Armory boosts task throughput over baselines by up to 18% on heterogeneous fleets in the real world.
🧵1/6
dave @ CoRL 2026 retweeted
Now accepted at #CoRL2026 ! See you in Austin.
Full release coming soon!
WAMs are popular because of their promise of better generalization. Is that true? We started playing with Video-Action-Model (VAMs) and realized a gap: video model backbones can compositionally generalize but VAMs often do not.
We coin this the Video-Action-Generalization (VAG) gap and present a study on how to explain and improve it. More details: umishra.me/temporal-ratio/
🧵 below
EgoWAM has been accepted to #CoRL2026 @corl_conf 🥳🥳 See you all in Austin!!!!
We’ve also open-sourced all the data and code:
📊 Data: partners.mecka.ai/egoverse?t…
💻 Code: github.com/GaTech-RL2/EgoWAM…
If you run into any problems, please submit an issue on GitHub. We’ll do our best to address it as soon as possible!
Egocentric human data is abundant, but human motion is not always positive supervision for robot policy due to embodiment gaps. Naive BC co-training can HURT performance ☹️.
🌟Our key finding in **EgoWAM**: the state-prediction branch of a World Action Model effectively bridges this embodiment gap, enabling robot performance to scale with diverse **in-the-wild** human data.
💡The key question then becomes: what world representation transfers best across embodiments?
👇🏻Let’s take a deep dive into it:
🌐 gatech-rl2.github.io/egowam.…
🧵[1/]
such an inspiring blog post. there is still so much you can learn from sim!
Behavioral cloning mystery
seohong.me/blog/behavioral-c…
I wrote a new blog post about "mysteries" in behavioral cloning that appear with real-world robot data (e.g., overfitting is "good"). I also tried to demystify them and shared my thoughts!
1
3
612
dave @ CoRL 2026 retweeted
Train on static objects. Grasp moving objects. 🤖
Many visuomotor policies assume static objects. Real deployments break this: parts drift on conveyors, fruits sway in the wind. Meet SIDO (Static In, Dynamic Out), taking a policy trained only on static demos to moving objects.
dave @ CoRL 2026 retweeted
Human data is the cheapest source of whole-body mobile manipulation demos. Turning it into robot data is the hard part.🤖
WARP retargets OFFLINE human motion into replayable robot actions in closed form — precise, consistent, faithful to whole-body intent.
🌍 warp-retargeting.github.io/




















