←
Lei Ye (Raymon Yip)60 posts
Lei Ye (Raymon Yip) avatar

Lei Ye (Raymon Yip)

@MasterYip3

PHD at Shanghai Institude of Technology (SII) & HIT Research Intern at Roboparty Lab AI & Robotics

◷ Joined February 2023▧ 9 Photos and videos
Lei Ye (Raymon Yip) avatar
Lei Ye (Raymon Yip)@MasterYip3·Oct 8

Can humanoid motion generation and control be unified in a single policy? PredActor uses a single end-to-end diffusion policy rather than separate motion generation and tracking. With proprioceptive feedback, it predicts internal future states and directly outputs actions at 50 Hz onboard a Unitree G1. Text-conditioned motion, joystick steering, disturbance response, and semantic interpolation are supported in the single policy. Project Page: masteryip.github.io/predacto…

1:17
Junior Rojas avatar
⟳ Lei Ye (Raymon Yip) retweeted
Junior Rojas@junior_rojas_d·Nov 16

trying to move heavier bodies

0:57
Kashu Yamazaki avatar
⟳ Lei Ye (Raymon Yip) retweeted
Kashu Yamazaki@kashu_yamazaki·Nov 14

Two years ago, we released Genesis, a universal physics engine for robotics. Today, I’m excited to announce 🍎 Eden — a robot learning framework built from the ground up for agents, unleashing full potential of Genesis. One task definition. From simulation to real robots. Sim-to-sim and sim-to-real just got easier. Coding agents build tasks 1.6–4× faster than in Isaac Lab. 🧵 1/11

1:36
AlexZ 🦀 avatar
⟳ Lei Ye (Raymon Yip) retweeted
AlexZ 🦀@blackanger·Nov 4

Computer use 需要进化到鼠标集群

0:40
Manthan Patel avatar
⟳ Lei Ye (Raymon Yip) retweeted
Manthan Patel@patelm99·Oct 28

Vision foundation models like DINO and SigLip now power much of robot learning. But they are built for RGB. What about depth? Introducing DeFM: a foundation model for depth images, built for robotics. 🌐 de-fm.github.io Weights, code, and demo are out today 🧵

0:13
Lokesh Krishna avatar
⟳ Lei Ye (Raymon Yip) retweeted
Lokesh Krishna@lok_s_h·Oct 30

orcs v0.1.1 is out 🚀 github.com/lok-i/orcs 🧗 perceptive whole-body locomotion task on EgoHTR: one adapted policy for rocky climbs and window crossing 🛠️ agentic UMR retargeting skill: leave frame-wise notes; your agent revises the reference

0:10
Chen Tessler @ CoRL avatar
⟳ Lei Ye (Raymon Yip) retweeted
Chen Tessler @ CoRL@ChenTessler·Oct 28

Coding agents can build an app. What if they could give it a body? Meet Metatron: a versatile System 1 controller for humanoids. A goal-based interface connects System 2 planners, including coding agents, to whole-body movement. A few examples below. 1/5

0:19
Chen Tessler @ CoRL avatar
⟳ Lei Ye (Raymon Yip) retweeted
Chen Tessler @ CoRL@ChenTessler·Oct 28

Project page: research.nvidia.com/labs/par… Code and model: github.com/NVlabs/ProtoMotio… Co-led with Yifeng Jiang, alongside our fantastic collaborators @AlecSaysThings , @YiShi_333 , @UmarIqb , @GalChechik , and @xbpeng4 .

Lei Ye (Raymon Yip) avatar
Lei Ye (Raymon Yip)@MasterYip3·Oct 27

Death stranding in real life!

Tz@Tz_2022Oct 26

这个太有意思了! 用 AI 决策模型 + Lidar 测距来实时评估并标记出远足登山过程中最合适安全的落脚位置,甚至还能区分左右脚。。。 一旦 AI 和物理世界打通,而且还能实时进行决策了,是真的前途不可限量哪。。。

0:51
Lei Ye (Raymon Yip) avatar
Lei Ye (Raymon Yip)@MasterYip3·Oct 27

I’m curious how Isaac Lab handles rendering. It doesn’t look like a traditional ray-tracing renderer, since I don’t see any noise in the figure. Maybe it’s using a game-engine renderer with some trade-offs? (path tracing on) But yes, I’ll buy it.

OVRTX is amazing

Post attachmentPost attachmentPost attachment
Kaibo He avatar
⟳ Lei Ye (Raymon Yip) retweeted
Kaibo He@KaiboHe·Oct 27

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…

0:50
Lei Ye (Raymon Yip) avatar
Lei Ye (Raymon Yip)@MasterYip3·Oct 26

Awesome results in contact handling!

Introducing Humanoid Mobility via Attention-based Contacts! One policy enables diverse motions over challenging terrains without reference motions at deployment. No manually designed transition motions No skill switching mechanism No manual data augmentation 13.2 minutes of data Click a goal and go! paper: tbd website: leggedrobotics.github.io/ACP…

1:58
Junzhe (JJ) He avatar
⟳ Lei Ye (Raymon Yip) retweeted
Junzhe (JJ) He@JayHe748646·Oct 23

Introducing Humanoid Mobility via Attention-based Contacts! One policy enables diverse motions over challenging terrains without reference motions at deployment. No manually designed transition motions No skill switching mechanism No manual data augmentation 13.2 minutes of data Click a goal and go! paper: tbd website: leggedrobotics.github.io/ACP…

1:58