Kaibo He

Research Scientist @CloneRobotics

[Kaibo He @KaiboHe]

@CaggianoVitt The checkpoint for both of the two models has been released! But I just trained to 10 hours. Also, I added a live demo on the project website😁

[Kaibo He @KaiboHe]

@srigopal Nope, code has been released, feel free to rerun it to see the results

[Kaibo He @KaiboHe]

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.

https://t.co/ZUpuqzVnAg

[Kaibo He @KaiboHe]

@BreezeOg1 Yes!

[Kaibo He @KaiboHe]

@ttktjmt Weight and live demo are released! Thanks for your interest

[Yanan Sui @YananSui]

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:
https://t.co/fc6matB2Pu

[Kaibo He @KaiboHe]

@ckli85 Open sourced musclemimic makes this happened

[Kaibo He @KaiboHe]

@qiayuanliao SuperMimic’s author

[jack @jack]

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.

https://t.co/r0qFLdvd6c

[Percy Liang @percyliang]

The final stretch...

[Kaibo He @KaiboHe]

OMG!!!!!!!

[Qiayuan Liao @qiayuanliao]

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: https://t.co/6gc9WKm9qY
Demo: https://t.co/OHRvx5ogQY

[Pieter Abbeel @pabbeel]

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

[Clone @clonerobotics]

Teleoperation of the Hand of Torso 3.

[Pulkit Agrawal @pulkitology]

@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.

[zeji yi @ZejiYi]

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 🧵

[Dream Labs @dreamlabs_ai]

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. 🧵

[Percy Liang @percyliang]

🚢Marin 535B-A23B training has crossed the halfway mark! Some observations and learnings so far:

[Kaibo He @KaiboHe]

@ckli85 @CherylWang39256 cool!

[Kaibo He @KaiboHe]

@ShanningZhuang 看的广是好的，但是分辨率太低啊，深度估计不准，还得有��类似头的移动平台装个高精度相机对焦到任务区域