Yixuan Pan

Robotics & AI PhD Student in HKU (The University of Hong Kong)
OpenDriveLab & HKU MMLAB
Humanoid; Scalable Learning

[Yixuan Pan @yixuanpan99]

🔥🔥🔥🔥

[Haoran Jiang @HRRiver_7]

What’s better than a humanoid playing ping-pong? Two playing doubles—and trying not to crash into each other 😁

Meet PingpongDuo: humanoid table tennis doubles 🏓

Check out the project and play with interactive 3D scenes
https://t.co/x0BatMNdjQ

Paper: https://t.co/N492sBfwFj

[Yixuan Pan @yixuanpan99]

Stay tuned for our tech report🫡

[Archon Robotics @Archon_Robotics]

🤖 Building Whole-Body Intelligence for the Real World. Were Just Getting Started.

From bending down to pick up objects and navigating steps to autonomously clearing tables, operating dishwashers, and organizing refrigerators, our robots are learning to perceive, move, manipulate, and coordinate their entire bodies in real-world environments.

Powered by our Whole-Body Intelligence (WBI) framework, were building generalist humanoid foundation models by combining large-scale human whole-body data pretraining, context-aware behavioral foundation models, and efficient post-training with real-robot data - turning human experience into real-world robotic skills.

👉 Watch Whole-Body Intelligence in action in our three-minute demo. More to come. Stay tuned at https://t.co/XSoqTfuZaD

#ArchonRobotics #WholeBodyIntelligence #WBI #Humanoid #PhysicalAGI

[Yixuan Pan @yixuanpan99]

Congrats! Great work from Hai!

[Hai Zhang @2318hhhz]

Our paper has been accepted to NeurIPS 2026!

Paris, it is less goo ! 🥐🥖

The first VA based navigation model — SparseVideoNav🔮🤖

Details: https://t.co/7451cFtcQB

See you in December ! 🇫🇷✨
#NeurIPS2026 #VLN #EmbodiedAI #Robotics

[Yichao Zhong @PeterYChong]

The ⚽️ #WorldCup2026 kicks off tonight 🏆 — and we're sending a humanoid onto the pitch too!

Meet RoboNaldo: a versatile humanoid football shooter.

It can strike the ball up to 13m/s, accurately lands within 17 cm of a 3 m target away, outdoors on real grass pitch, off a live human pass, with fully onboard perception.

https://t.co/iFV7bINU2p

🧵👇

[OpenDriveLab @OpenDriveLab]

UMI made robot data collection intuitive.
🤖 TAMEn takes it further — bringing vision and touch into a unified, closed-loop learning system.
🌏 https://t.co/wkT2y1fFwz
📑 https://t.co/YZMsgFgth0
🔗 https://t.co/ITRNRG570p

✨ What’s new:
- Dual-mode data collection (MoCap ↔ VR)
- Online replayability check
- AR-in-the-loop + real-time tactile feedback (tAmeR)
- Self-evolving pyramid data pipeline

🚀 Results:
34% → 75% success rate on bimanual tasks.
This marks a shift from usable data to self-improving data engines.
TAMEn turns robots from "blind operators" into tactile-aware, evolving collaborators.

#EmbodiedAI #Tactile #Robotics #Bimanual #TAMEn

[Yixuan Pan @yixuanpan99]

Solid work from Haochen!!!
Let's learn at scale🫡🫡

[Haochen Tian @HCTian713]

SimScale is selected as CVPR 2026 Oral 🎉🥳

Code, simulation data, and checkpoints have been fully open-sourced.

📷Home: https://t.co/ejTgqZ3NbW
📷Paper: https://t.co/euJW2MOtOE
📷Github: https://t.co/AxuTMvqVGk

If you find something useful, please give it a star⭐

[JunLi Ren @junli_r84995]

paper released！ https://t.co/34C7WWGVQR
project website https://t.co/k2RgUQVvu6

[Yixuan Pan @yixuanpan99]

@Jia_Fei_Yu Solid!

[Yixuan Pan @yixuanpan99]

Stay tuned to our work!

[JunLi Ren @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!

[Yixuan Pan @yixuanpan99]

Again! Solid work from Jiazhi!!

[Jiazhi Yang @jiazhi_yang2024]

🧐Applying world models to improve real-world policy on challenging manipulation tasks used to be considered out of reach.

😌After sustained effort, we’re now seeing encouraging progress.

🚀Thrilled to introduce RISE: Self-Improving Robot Policy with Compositional World Model

https://t.co/eP1EOmk2X1
https://t.co/mEa2SsZAZ1

RISE is, to our knowledge, the first work to use a world model as an effective learning environment for challenging real-world manipulation, enabling policy improvement on tasks that demand high dynamics, dexterity, and precision.

Incredible teamwork with @lin_kunyang111 @francislee2020 @YueXiangyu @HaoZhao_AIRSUN @smch_1127

[Ruoyi Qiao @_ruoyiqiao]

Update: We’ve open-sourced the motion components of AMS! 🐙
- Synthetic Motion Dataset
- Balance Motion Generation Pipeline

More details in the repo ↓
🔗 https://t.co/lYyloM8UF2

[OpenDriveLab @OpenDriveLab]

https://t.co/7uGphEXxjk

[Shenyuan Gao @ShenyuanGao]

🤖 How can we enable zero-shot generalization to unseen scenarios for robot world models?

Thrilled to share DreamDojo 🌎 — an interactive robot world model pretrained on 44K hours of human egocentric videos, the largest and most diverse dataset to date for robot world model learning. Our model not only excels in generalization, but also supports real-time interaction at 10 FPS after distillation. It enables several important applications, including live teleoperation, policy evaluation, and model-based planning at test time.
🔗 Project: https://t.co/hJIEiGXnKz
📰 Paper: https://t.co/oa5xr8Y2GH
🤗 Code & models & datasets: https://t.co/A8B4ii0Kah

#WorldModels #Robotics #EmbodiedAI #RL #AI #NVIDIA

Sharing more details in the thread 🧵

[Yixuan Pan @yixuanpan99]

@ROA_Studio @zhengyiluo The humanoid imitates the human pose captured by VR device.

[Yixuan Pan @yixuanpan99]

Just saw Sonic — it’s incredibly solid. By far the best whole-body control model I’ve seen so far. It opens up an invaluable path to acquiring full-body coordination data for humanoid robots. Huge congrats to the team and big thanks for open-sourcing it! 🙌🔓

[Zhengyi “Zen” Luo @zhengyiluo]

SONIC is now open-source!

Generalist whole-body teleoperation for EVERYONE!

Our team has long been building comprehensive pipelines for whole-body control, kinematic planner, and teleoperation, and they will all be shared.

This will be a continuous update; inference code + model already there, training code and gr00t integration coming soon!

Code: https://t.co/7u3SBxzXU9
Docs: https://t.co/HpDLkTCSMF
Site: https://t.co/D3i4KlnLLr

[Yixuan Pan @yixuanpan99]

@zhengyiluo Huge congrats to the team and big thanks for open-sourcing it!

[Chonghao Sima @smch_1127]

Huge shoutout to the entire team and everyone involved behind the scenes! 🙌

KAI0 is going fully open-source this week. 🚀

📄 Paper: https://t.co/wnKu2nKzKD 💻 Code: https://t.co/LqrT7D4bSV

Feedback, comments, and ⭐️s are very welcome!

#Robotics #OpenSource #EmbodiedAI #kai0

[Modi Shi @idomihs]

[1/n]
The bottleneck: collecting humanoid teleoperation data is expensive, slow, and trapped in labs. But robots need to work in homes, stores, and outdoors — environments they've never trained in.
Our key insight: humans already perform these tasks every day, everywhere.

[Jiazhi Yang @jiazhi_yang2024]

RISE (1/N)

Before diving into technical details, let's first see what we've achieved on challenging manipulation.

RISE yields absolute performance increases of:
+45% in Backpack Packing
+35% in Box Closing
+35% in Dynamic Brick Sorting
compared to a strong offline RL method (RECAP, re-implementated on pi_0.5, which is an amazing work by @physical_int)

These improvements highlight the effectiveness of leveraging a proper world model for policy optimization for contact-rich manipulation.

[Chonghao Sima @smch_1127]

Glad to share me and my folks work of the last research cycle, good luck and have fun. Upvote on HF is appreciated!

χ0: https://t.co/9fGaZXVeID

χ0, a resource-efficient robotic manipulation framework addresses distributional shifts through model arithmetic, stage-aware advantage estimation, and train-deploy alignment to achieve long-horizon task reliability.

RISE: https://t.co/JygfMDCMw0

RISE, the first work to use a world model as an effective learning environment for challenging real-world manipulation, enabling policy improvement on tasks that demand high dynamics, dexterity, and precision.

EgoHumanoid: https://t.co/LsxLyqgQBf

EgoHumanoid, the first endorsement of human-to-humanoid transfer for whole-body loco-manipulation.

SparseVideoNav: https://t.co/zhZKlPM9AI

Vision-language navigation systems traditionally require detailed instructions but can be improved by incorporating video generation models with sparse future planning for faster, more efficient real-world deployment.