Kaibo He (@KaiboHe) profile picture

Research Scientist @CloneRobotics

San Francisco, CA
Joined April 2022
Photo by Kaibo He (@KaiboHe)Photo by Kaibo He (@KaiboHe)
Kaibo He retweeted
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
46
119
34
924
119,115
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…
79
64
23
1,233
75,823
🎉 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
1
2
9
293
Kaibo He retweeted
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
12
142
18
1,009
68,014
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…
16
44
8
333
22,345
Kaibo He retweeted
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…
8
16
783
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…
14
29
7
280
20,913
@qiayuanliao SuperMimic’s author
4
1,022
Kaibo He retweeted
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
4,163
7,132
4,763
68,994
13,789,172
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…
11
13
1
241
21,086
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/
19
68
8
694
54,889
Kaibo He retweeted
Teleoperation of the Hand of Torso 3.
49
131
39
1,123
229,161
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.
88
109
71
1,025
135,267
Kaibo He retweeted
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 🧵
13
49
12
289
31,293
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. 🧵
157
184
167
1,677
633,549
Kaibo He retweeted
🚢Marin 535B-A23B training has crossed the halfway mark! Some observations and learnings so far:
23
100
10
1,075
72,663
Protoclone, the world's first bipedal, musculoskeletal android.
7,679
6,455
19,627
53,683
52,666,759
Welcome to the Clone World! clonerobotics.com
58
75
44
916
157,944
Introducing Torso, a bimanual android actuated with artificial muscles.
629
1,505
1,604
10,238
3,602,130