
Research Scientist @CloneRobotics
San Francisco, CA
Joined April 2022
- Tweets31
- Following127
- Followers142
- Likes106
Introducing ⚡️Flash ALOHA: Learning Fast and Precise Manipulation!
With just 50 demonstrations, Flash ALOHA learns to autonomously complete dynamic and precise tasks at near human speed.
Everything open sourced!
(1/11)
Team:
@Qi_Wu577 @YihuaiGao @chelseabfinn @zipengfu – at Stanford, CA
Kaibo He retweeted
SuperMimic has won the CORL’s best paper award. Thanks for everyone’s support!
SuperMimic is open-sourced during my talk at CORL.
Have fun with it: github.com/HybridRobotics/su…
Kaibo He retweeted
🎉 MyoSuite 3.1.0 is here!
Explore muscle-driven movement in complex environments, including terrain-aware control.
This teaser features TERRA — thanks to @amathislab
Ready to explore? Check out MyoSuite and see what you can build:
github.com/MyoHub/myosuite
MuJoCo 4.0 is out!
• Fast or thin objects no longer pass through each other
• Soft bodies can now deform permanently and rods can twist
• MuJoCo Studio, the successor to simulate, with physically based rendering via Filament
Try it live: mujoco.org
Kaibo He retweeted
How about: Whole-body motion tracking for the Unitree G1 in under a minute :)
XMimic trains one policy on all 40 LAFAN1 clips in 54 seconds on 4 H100s.
3.5x faster than BlinkMimic and 85x faster than SuperMimic.
Code: github.com/nico-bohlinger/xm…
Report: nico-bohlinger.github.io/pap…
General Whole-Body Controller for Human Musculoskeletal Systems. MS-Emulator enables MS-Human-700 to achieve precise tracking of diverse movements. Towards foundation models for human motor behavior.
Interactive Demo:
lnsgroup.cc/research/MS-Emul…
Three years ago, training a walking policy for this 700-muscle humanoid took 2 days, using a CPU simulator and SAC. That was for a single motion. Today, with SuperMimic and MJWarp, it learns to track 1.5 hours of motion capture in 4 hours on one 5090.
muscle-supermimic.beanpow.to…
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence.
block.xyz/dessa
Kaibo He retweeted
The final stretch...
Marin's 535b is now >80% through pretraining! Here’s loss vs. our scaling-ladder forecasts. The sharp drop comes with the 4K→16K context switch, so we're kind of cheating the forecast. (This was planned.) We'll re-eval at 4k too. forge.coreweave.com/wandb/ma…

ALT Forecast versus observed loss: Hero’s evaluation loss falls below both scaling-ladder forecasts, reaching 1.528 at step 314,999. A sharp drop accompanies the switch from 4K to 16K context near step 258,000, making subsequent values not directly comparable with the 4K forecasts. The cooldown mixture begins at step 312,192.
OMG!!!!!!!
We found a way to scale humanoid control that reduces GPU-hours by more than 1000×.
Across 129,514 motions, SuperMimic surpasses the state of the art (128 GPUs, 7 days) with 1 GPU in 3 hours.
Project: supermimic.github.io
Demo: supermimic.github.io/demo/
3
366
Kaibo He retweeted
Game changer for humanoid full-body control training. Now it's superfast (and cheap, just one GPU) to train a single policy on *all* the motions. How come:
(1) World model much faster than regular sim
(2) Backprop through time collects way more signal than policy gradients
We found a way to scale humanoid control that reduces GPU-hours by more than 1000×.
Across 129,514 motions, SuperMimic surpasses the state of the art (128 GPUs, 7 days) with 1 GPU in 3 hours.
Project: supermimic.github.io
Demo: supermimic.github.io/demo/
Kaibo He retweeted
Replying to @EkaRobotics
@EkaRobotics has raised a $150M Series A.
Generality v/s Performance is the fundamental tension at the frontier of robotics. Generality without performance is just a prototype. Performance without generality is just a single-purpose tool.
Customers shouldn’t have to choose. Eka breaks the tradeoff. Powered by our Vision-Force-Action (VFA) model, we deliver the performance and versatility customers need to put robots to work every day.
Eka is built on three convictions:
⚡️Force is the language of manipulation.
🚀 Reinforcement learning is how dexterous manipulation scales.
🎂 System 1—fast, reliable physical execution—is the bottleneck to solve.
With this funding, we will scale our model and accelerate customer deployments.
Grateful to be building alongside a dream team and investors who share our ambition.
Common belief: Robot policies need continuous action heads; discrete actions are 𝐥𝐞𝐬𝐬 𝐧𝐚𝐭𝐢𝐯𝐞 𝐚𝐧𝐝 𝐥𝐞𝐬𝐬 𝐩𝐫𝐞𝐜𝐢𝐬𝐞.
❗We find policies w/ the simplest discrete representations 𝐦𝐚𝐭𝐜𝐡 𝐨𝐫 𝐛𝐞𝐚𝐭 continuous ones—in sim & real, in single-step & diffusion/flow settings.
Here's why 🧵
Kaibo He retweeted
Today, Dream Labs is coming out of stealth with Dream-1, a robot foundation model that controls bimanual robots it has never seen, on tasks it was never shown, in places it has never been, from $3/hour.
Dream API is live for everyone, today. 🧵
Kaibo He retweeted
🚢Marin 535B-A23B training has crossed the halfway mark! Some observations and learnings so far:
Kaibo He retweeted
Welcome to the Clone World! clonerobotics.com

















