Tao Huang

PhD @ Shanghai AI Lab & SJTU | MPhil @ CUHK | B.Eng. @ ShanghaiTech

[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

[Yitang Li @li_yitang]

Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 https://t.co/3VdyRWgOqb

🧩ONE latent space for ALL tasks
⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy
🤖Natural recovery & transition

[Guangqi Jiang @LuccaChiang]

Ever want to enjoy all the privileged information in sim while seamlessly transferring to the real world? How can we correct policy mistakes after deployment?

👉Introducing GSWorld, a real2sim2real photo-realistic simulator with interaction physics with fully open-sourced code.

[Tao Huang @TaouHuang]

Try our latest humanoid goalkeeper! I cannot score against him😂

[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]

@LuccaChiang Thanks gq!

[Tao Huang @TaouHuang]

Thanks to my wonderful collaborators: @HuayiWang04 , Junli Ren, Kangning Yin, Zirui Wang, @XiaoChen_Twi, @Jia_Fei_Yu, Wentao Zhang, @junfeng_long, @Alex_wangjingbo, @pangjiangmiao.

[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

[Tao Huang @TaouHuang]

Check our HSI system in the physical world!

[Huayi Wang @HuayiWang04]

💡 How can humanoids achieve autonomous, generalizable, and lifelike interactions with real-world objects?
🤖 Introducing PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System

Paper: https://t.co/k7iykFXjn8
Website: https://t.co/eC3oQvsLKt

[Huayi Wang @HuayiWang04]

💡 How can humanoids achieve autonomous, generalizable, and lifelike interactions with real-world objects?
🤖 Introducing PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System

Paper: https://t.co/k7iykFXjn8
Website: https://t.co/eC3oQvsLKt

[机器之心 JIQIZHIXIN @jiqizhixin]

📬 #PapersAccepted by Jiqizhixin

GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes

Project: https://t.co/HXSDkeHowc
Code: https://t.co/Xq4k6i2Dbx
Paper: https://t.co/zm5XSJwV5d

[Xiao Chen @XiaoChen_Twi]

#ICCV2025
🤔 How to scan and reconstruct an unseen collision-rich indoor scene with 10+ rooms?
💡 Our answer is "Launch the drone; Let it map".

🤖 Thrilled to introduce GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes.

[Tao Huang @TaouHuang]

HoST is selected as a Best Systems Paper Finalist at #RSS2025!
Presentation today:
Spotlight Talks: 4:30pm-5:30pm
Poster: 6:30pm-8:00pm Board Nr: 22
Welcome to our poster and have a zoom chat with us!

[Tao Huang @TaouHuang]

💡Can a humanoid robot learn to stand up across diverse real-world scenarios from scratch?

🤖 Introducing HoST: Learning Humanoid Standing-up Control across Diverse Postures

Website: https://t.co/BExxVLpT5C

[Tao Huang @TaouHuang]

The standing-up motion is very similar to our motions on Unitree G1😃Code is available: https://t.co/ghq8LlcOAD

Happy to see humanoid standing-up control get better!

[The Humanoid Hub @TheHumanoidHub]

LUS 2 by Lumos Robotics: Lying flat on the floor to vertical in 1 second.

[Tao Huang @TaouHuang]

@corl_conf Hi. It seems that we cannot add authors between the abstract submission deadline and the final submission deadline. But this information is seemingly not listed on the website. Could you please kindly check that? Thx!

[Tao Huang @TaouHuang]

Our work on manipulation-centric representation from large-scale robot dataset will be presented in ICLR. Catch Huazhe @HarryXu12 on the site for more details!

[Guangqi Jiang @LuccaChiang]

Our #ICLR2025 paper MCR will be presented at Hall 3 + Hall 2B #42 on Apr 24th from 7:00 to 9:30 PM PDT. Won't be able to attend the conference since I'm working on CoRL submission. Please check it out and drop me an email if you are interested!

[Sizhe Yang @SizheYang111]

💡 With a single manually collected demonstration, can the learned policy achieve robust performance?

🤖 #RSS2025 Introducing RoboSplat: Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation

🔗: https://t.co/5MnRFrfiZz

[Yuanchen Ju @ju_yuanchen]

🧩#CVPR2025🌷Introducing Two By Two✌️: The First Large-Scale Daily Pairwise Assembly Dataset with SE(3)-Equivariant Pose Estimation.
🤖2BY2 helps robots master daily 3D assembly tasks—like plugging sockets or arranging flowers—across diverse objects!
🐨Co-lead by @yuqi_Beijing

[Tao Huang @TaouHuang]

@LuccaChiang Thanks Guangqi!

[Tao Huang @TaouHuang]

@Xialin_He Thanks Xialin! Congratulations to HumanUP too. It is a very nice work. See you in USA in June🤩

[Tao Huang @TaouHuang]

HoST is accepted to #RSS2025!
Code is open-sourced: https://t.co/ghq8LlcOAD

💡Training code of Unitree G1 and H1
💡Tip of extension to other humanoid robots
💡Hardware deployment tips (G1 & H1-2)
- Diverse terrains | supine | prone postures
- Evaluation and visualization scripts

[Tao Huang @TaouHuang]

💡Can a humanoid robot learn to stand up across diverse real-world scenarios from scratch?

🤖 Introducing HoST: Learning Humanoid Standing-up Control across Diverse Postures

Website: https://t.co/BExxVLpT5C

[Tao Huang @TaouHuang]

@cixliv The rubber hands are broken during the deployment, guess they are too soft to support the large weight. So we remove the hands. The arms seem good enough. But significant deviations of upper-body joints between real and sim are found. Still a long way to go🙂

[Tao Huang @TaouHuang]

@liangpan_t Thanks Liang🤩