Vector Wang

PhD student in robotics manipulation @RiceCompSci. Creator of XLeRobot. Prev Nvidia.

[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]

Agentic Robotics Workshop is also extending our Live Demo Call!

Run your agent (LLMs, VLAs as tools, memory, recovery) on our Unitree G1 or AgileX dual-arm, or bring your own robot.
https://t.co/N2W7d8id5y

[Georgia Chalvatzaki @GeorgiaChal]

🚨 Attention, Robot Learning community!

For the first time, @corl_conf is introducing a Call for Late-Breaking Results, focusing on Agentic Robotics and Real2Sim2Real!

Research is moving fast, and we want to make room for important new results as they emerge!

📅 Deadline: October 26 #CoRL2026

🔗 https://t.co/scbWwgVAr1

[Vector Wang @VectorWang2]

@YorkYang5050 Thanks York! Just a simple demo. What I like most about mujoco web is that you can even play with it on your phone.

[Vector Wang @VectorWang2]

@BrianZheng103 https://t.co/scIS0Gti4d

[Vector Wang @VectorWang2]

Replicated the laundry task in mujoco web, and also self-trained the RL WBC. By Opus 5.5 in 3 hrs.
Agentic real2sim is nearly solved.

[Marilyn Liu @MarilynLiu97]

Inspired by the discussion between @qiayuanliao and @wenlong_huang, @kun_h____'s explanation, and insights from Pengxiang and Junfeng. I admire @DynaRobotics' thoughtful choices and look forward to what's next. https://t.co/NO7ZQWuSPW

[Vector Wang @VectorWang2]

@LeoKharon https://t.co/scIS0GsKeF

[Vector Wang @VectorWang2]

@HairuoL81560 https://t.co/scIS0GsKeF

[Vector Wang @VectorWang2]

Open-sourced and you can play with it directly on web:
https://t.co/scIS0GsKeF

[Vector Wang @VectorWang2]

@acrosson Basically I pre-baked the lighting using blender first.

[Vector Wang @VectorWang2]

@newuhe ~98% synthetic (random keyframes + min-jerk + step targets → FK), seeded by ~97 s of Dyna's public ego-replay clips

[Vector Wang @VectorWang2]

@acrosson Mujoco web, so I can have additional renders customized (while still runs in real time in the browser)

[Vector Wang @VectorWang2]

@haitong__wang Currently all rigid bodies so it's easier to run on web.

[Vector Wang @VectorWang2]

@Lindon_Gao Thanks Lindon! Thrilled to get acknowledged by you. I am always fascinated by what Dyna has done.

[Vector Wang @VectorWang2]

@gaofeng220 The robot trajectory is retrieved from official website (only kinematic) and Opus did the scene and robot dynamics to match this trajectory.

[Vector Wang @VectorWang2]

@HairuoL81560 After I confirm with Dyna, it’s their IP after all

[Vector Wang @VectorWang2]

@SaketTiwari14 Mujoco supports cloth simulation, but the performance is not good and can't really do real-time in web. So in the video the cloth is only presented as rigid body.

[Vector Wang @VectorWang2]

@leo_stalemate Mujoco supports cloth simulation, but the performance is not good and can't really do real-time in web. So in the video the cloth is only presented as rigid body.

[Vector Wang @VectorWang2]

@thejerrycheng Robot file is extracted from Dyna's website and added physical properties, and also generated collision mesh. Didn't use special designed harness, just prompted my requirements in claude code.

[Vector Wang @VectorWang2]

A fun project I vibed early this year just got featured on world labs! @theworldlabs

Come check it out and play on web:
https://t.co/cwLKH6prJ8

[Vector Wang @VectorWang2]

@HaixuanT @NVIDIARobotics Congrats! And fun to see you in HF shirt (though also part of NV) lol