Junfeng Long

Ph.D. student @UCBerkeley. Working on reinforcement learning and humanoid robots.

[Junfeng Long @junfeng_long]

@NVIDIAGeForce PRAGMATA RTX

[Junfeng Long @junfeng_long]

Fei!

[Feiyu Jia @Jia_Fei_Yu]

🙌Feel Robot Feels: Tactile Feedback Array Glove for Dexterous Manipulation

Project website:https://t.co/9MAeMPKkA6
Paper:https://t.co/nHlBVy2zIE

Stay tuned—code will be open-sourced shortly! [🍻]

[JunLi R @junli_r84995]

sharing our new project Smash!🏓
We built the first outdoor humanoid table tennis player with fully onboard perception — no MoCap, no external cameras. check the video for details.
paper and code on the way!

[Junfeng Long @junfeng_long]

Very cool humanoid tennis demo. Turns out solving humanoid robotics requires a bit more than overfitting to mocap clips in unrealistic scenes.

[Zhikai Zhang @Zhikai273]

🎾Introducing LATENT: Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data

Dynamic movements, agile whole-body coordination, and rapid reactions. A step toward athletic humanoid sports skills.

Project: https://t.co/MFy2NIOsrn
Code: https://t.co/A7B5H8PIBh

[Qiayuan Liao @qiayuanliao]

Happy to see my code could solve the problems my labmate previously refused to tackle until I made it easy.
Funny how it turned into a scoop of my own PhD thesis topic, but glad the tools work. 🙃

[XueYeiii @XueYeiii9]

Can a single learned controller generalize across diverse humanoid embodiments?

Introducing XHugWBC, a novel cross embodiment training framework that enables generalist humanoid control through:
1) physics-consistent morphological randomization
2) unified state-action representation with semantic alignment across different robots
3) graph-based policy for cross-humanoid control

We find that a single policy can zero-shot generalize to unseen robots with one-time training. The resulting generalist policy reaches approximately 85% of the performance achieved by the specialist, and the fine-tuning generalist shows approximate 10% improvement compared to the generalist policy.

🔗Website:https://t.co/0uwNiHxrq3
📕 Arxiv:https://t.co/UVj0rgIi4A

[Junfeng Long @junfeng_long]

Cool! By isolating the actual mechanisms behind generative control performance, this paper encourages a much-needed rethinking of modern robot policy design.

[Chaoyi Pan @ChaoyiPan]

Generative models (diffusion/flow) are taking over robotics 🤖. But do we really need to model the full action distribution to control a robot?

We suspected the success of Generative Control Policies (GCPs) might be "Much Ado About Noising."

We rigorously tested the myths. 🧵👇

[Junfeng Long @junfeng_long]

Hang!

[Hang Liu @Hang_Liu02]

Pixels in, contacts out...

Perception, interaction, autonomy - next agenda for humanoids.

We learn a multi-task humanoid world model from offline datasets and use MPC to plan contact-aware behaviors from ego-vision in the real-world.

Project and Code: https://t.co/4SRJ1qD196

[Junfeng Long @junfeng_long]

AMP still has its privilege in the motion tracking era!

[JunLi R @junli_r84995]

⚽️ We create a humanoid goalkeeper !
🥅One-stage RL training
⏰Fully autonomous & real-time
📷Alternative perception: MoCap ↔️ onboard camera
🔁 Generalizes to ball grabbing, squat & jump escapes
website: https://t.co/yBFT5xmiMQ
paper: https://t.co/prx9qaH3ej

[Tao Huang @TaouHuang]

💡 How can humanoids learn adaptable skills from a single human motion?
🤖 Introducing AdaMimic: Towards Adaptable Humanoid Control via Adaptive Motion Tracking

Paper: https://t.co/fJBxNPZKeF
Website: https://t.co/nVPh3yZKrf

[Junfeng Long @junfeng_long]

@NVIDIAGeForce GeForce Day

[Junfeng Long @junfeng_long]

😍

[Kevin Zakka @kevin_zakka]

Meet mjlab. Powered by MuJoCo Warp. Drops Monday.

[Junfeng Long @junfeng_long]

@haoshu_fang @umdcs congrats！

[Junfeng Long @junfeng_long]

Really amazing work done by Zhi in 3 months as an undergraduate. He is now applying for PhD!

[Zhi Su @ZhiSu22]

🏓🤖 Our humanoid robot can now rally over 100 consecutive shots against a human in real table tennis — fully autonomous, sub-second reaction, human-like strikes.

[Kaizhe Hu @hkz222]

How do we learn motor skills directly in the real world? Think about learning to ride a bike—parents might be there to give you hands-on guidance.🚲

Can we apply this same idea to robots?

Introducing Robot-Trains-Robot (RTR): a new framework for real-world humanoid learning.

[Junfeng Long @junfeng_long]

What a gift to the humanoid community and thanks for the release!

[Qiayuan Liao @qiayuanliao]

Want to achieve extreme performance in motion tracking—and go beyond it? Our preprint tech report is now online, with open-source code available!

[Junfeng Long @junfeng_long]

@xiaolonw Congrats!

[-T.K.- @t_k_233]

Humanoid robots should not be black boxes 🔒 or budget-busters 💸!

Meet Berkeley Humanoid Lite!
▹ 100% open source & under $5k
▹ Prints on entry-level 3D printers—break it? fix it!
▹ Modular cycloidal-gear actuators—hack & customize towards your own need
▹ Off-the-shelf parts—NO custom PCBs, NO CNCs

Built on 4 years of R&D to put humanoid robotics in everyone's reach.

Website: https://t.co/Fz8QRjq6Rj
Documentation: https://t.co/fZeQlZQ16k

[Junfeng Long @junfeng_long]

@zeqi_xiao 这么帅！

[Boston Dynamics @BostonDynamics]

Atlas is demonstrating reinforcement learning policies developed using a motion capture suit. This demonstration was developed in partnership with Boston Dynamics and @rai_inst.