Vector Wang

PhD student in robotics manipulation, currently on physics-aware world models for robust manipulation @RiceCompSci. Designer and developer of XLeRobot.

[Vector Wang @VectorWang2]

Catching a flying ball is hard. What if with a flat plate? 🏓

Our work at RSS’26 shows it’s possible through Zero-Shot Sim2Real

With Domain-Randomized Instance Set (DRIS), we catches different kinds of balls without any real-world fine-tuning

🔗 https://t.co/7qqcjlWiiY

[Vector Wang @VectorWang2]

@ahadj0 planning to buy an inflatable one actually lol

[Vector Wang @VectorWang2]

Started my research internship in the NVIDIA Seattle Robotics Lab. Mostly working on agentic robotics.

In Seattle this summer and ready to hang out with new/old friends!

[Caelan Garrett @CaelanGarrett]

I’ll be at #ICRA2026 in Vienna presenting ScheduleStream, our work on GPU-accelerated multi-arm task and motion planning: https://t.co/PbB7sCxSBY

If you’re looking to meet to chat about NVIDIA, schedule time here: https://t.co/VpCxNfpCzH

[Vector Wang @VectorWang2]

@gs_ai_ Really cool work! Can wait to experience it. Great contribution to the field.

[High Torque Robotics @HTrobotics]

🚀 Panthera-HT is here — the cost-efficient robotic arm that doesn't compromise performance. Only $1,799.3.5kg payload | 0.8m/s speed | ≤140μs response Fully open-source (MIT) | LeRobot-native | ROS2 ready

#Robotics #OpenSource #EmbodiedAI #LeRobot #XLeRobot

[Vector Wang @VectorWang2]

This is really professional

[Ryan Chan @Ryan_Resolution]

Setting up with @IsaacSin12 for our upcoming hackathon

This is part of our @makermodsai Physical AI Hack World Tour.

We’re introducing OpenBooth, our new foldable physical AI lab. If you want a grab one for yourself, move quick coz we are selling out fast.

This is a massive robotics hackathon here in @fdotinc. Just putting in some final few touches on our robots and OpenBooth setups for our hacker tomorrow.

[Isaac Sin @IsaacSin12]

.@NVIDIARobotics is joining the SF Physical AI Hackathon as a sponsor

Every team gets Brev credits to train models on cloud GPUs.

Win the hackathon and walk away with a Jetson Orin Nano Super ! + Brev credits

May 9–10 · @fdotinc Fort Mason, SF
RSVP → https://t.co/WFuAASj0nB

[Vector Wang @VectorWang2]

@sentientcar this case it won’t make the full use of the soft finger?

[Vector Wang @VectorWang2]

@HelmickAlan Actually the first author of this paper has also participated in that work

[Vector Wang @VectorWang2]

Catching a flying ball is hard. What if with a flat plate? 🏓

Our work at RSS’26 shows it’s possible through Zero-Shot Sim2Real

With Domain-Randomized Instance Set (DRIS), we catches different kinds of balls without any real-world fine-tuning

🔗 https://t.co/7qqcjlWiiY

[Vector Wang @VectorWang2]

We put DRIS to the test with a highly demanding task: reactive catching using a completely flat plate on a Franka Robotics FR3 @FRANKAROBOTICS robot. Unlike robotic systems that rely on cups, nets, or enclosing surfaces for passive stabilization, our setup offers zero mechanical help, making it extremely sensitive to contact timing and noise.

[Vector Wang @VectorWang2]

Accepted at Robotics: Science and Systems (RSS Conference) 2026:

"Zero-Shot Sim-to-Real Robot Learning: A Dexterous Manipulation Study on Reactive Catching."

Authors:Kejia Ren¹, Gaotian Wang¹, Andrew S. Morgan², Kaiyu Hang¹
¹Rice University ²Robotics and AI Institute

[Vector Wang @VectorWang2]

Same as ManiDreams, this task is also fully trained within Maniskills @Stone_Tao 😂😂

[Vector Wang @VectorWang2]

Here is how it works: 

Instead of training on one randomized instance at a time, DRIS propagates multiple randomized instances simultaneously under a shared action. 

By allowing the policy to learn from a set of possible dynamics outcomes at once, it becomes remarkably robust to variations in physical properties and sensing errors

[Isaac Sin @IsaacSin12]

We're building the UI @LeRobotHF should have shipped with

Plug in your SO101 or XLeRobot, scan your ports and cameras, auto-calibrate, and you're teleoperated in under 5 minutes. No terminal.

[Vector Wang @VectorWang2]

@pkuhar In US the official price for the large arm is ~2k$, ~1.4k$ in China. I am building a smaller version myself using their cheaper motors.

[Vector Wang @VectorWang2]

Building up a mini Tidybot for <$2k in total.

More dynamic (realtime no speed up) and more robust

Plugged into upcoming X-bot universe with OpenClaw agentic applications.
https://t.co/DYI989ZaAl

[Vector Wang @VectorWang2]

@pkuhar The arm is ～1k$ if assemble it yourself, all parts are open sourced

[Vector Wang @VectorWang2]

@kamathsblog Here's the step file of the wheel base https://t.co/GGBkdQudgU

[Vector Wang @VectorWang2]

@pkuhar no, currently using an odrive 3.6 board