←
Vector Wang535 posts
Vector Wang avatar

Vector Wang

@VectorWang2

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

◷ Joined November 2021▧ 199 Photos and videos
Vector Wang avatar
Vector Wang@VectorWang2·Apr 30

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 🔗 rice-robotpi-lab.github.io/D…

1:18
Vector Wang avatar
Vector Wang@VectorWang2·22h

Simulation is actually much "easier" to build and validate nowadays compare to 6 months ago. We need a community effort for a fully built, fully functional (in multiphysics, speed, and renders) and well maintained benchmark soon.

Post attachment

What does RoboDojo really simulate? We followed it from the real world to its score, one link at a time. At almost every step, it simulates something other than what it says. Same bottle, same grasp. As shipped, it tips 78° in the hand. After our fix, it stays level.

0:04
Vector Wang avatar
Vector Wang@VectorWang2·Nov 12

This is wild

Post attachment

Join us this afternoon 2pm at Agentic Robotics Workshop at CoRL! Great speakers from UC Berkeley @Ken_Goldberg , CMU @GuanyaShi , NVIDIA, Gemini Robotics, Dexmate, and Tencent! And enjoy cool agentic demos! Location: JW Room 203-204 Demo: Griffin Room (2nd floor)

Dyna Robotics avatar
⟳ Vector Wang retweeted
Dyna Robotics@DynaRobotics·Nov 9

Yesterday, we unboxed Taku at @corl_conf put it to work. Powered by Dyna-2.1, it performed long-horizon, whole-body mobile manipulation zero-shot, with no on-site data collection or post-training. Come see it live and meet the team at Booth 500 in Griffin Hall!

0:41
Soha Pouya avatar
⟳ Vector Wang retweeted
Soha Pouya@SohaPouya·Nov 7

Heading to #CoRL2026 in Austin? Catch @NVIDIARobotics at @DrJimFan's keynote, @Dr_YanChang 's V2D Challenge, @TuurStuyck's Isaac Lab Arena updates, Nvidia booth (GR00T, Isaac Lab, Newton), our research reception on Nov 11 and many more exciting updates lined-up here: nvidia.com/en-us/events/corl… I’ll be there too and looking fwd to catching up with the vibrant CoRL community - Feel free to DM to connect!

Jason Ma avatar
⟳ Vector Wang retweeted
Jason Ma@JasonMa2020·Nov 1

This is already the present for SOTA robotics architecture

Post attachment

let me predict the future robotics architecture: > System 2: LLM agents for long-horizon planning, task decomposition, tool/skill use, memory, and closed-loop replanning. mostly agentic harness + function calling. > System 1: A new hybrid VLA-WAM policy architecture. It will jointly model future world states + actions. MOT / dual-expert backbone. It will output action chunks or motion tokens. > System 0: A small (~10M to 100M) learned whole-body controller / tracking policy. it will convert sys 1 outputs into joint/torque commands w balance, contact, dynamics, and safety constraints. trained via RL + human motion priors.

Vector Wang avatar
Vector Wang@VectorWang2·Oct 20

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. lnkd.in/gZXmWcZC

🚨 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 🔗 corl.org/contributions/call-…

Vector Wang avatar
Vector Wang@VectorWang2·Oct 13

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.

0:30

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.

Reward AI avatar
⟳ Vector Wang retweeted
Reward AI@RewardAI_·Sep 14

Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids. - learned directly from human manipulation data - no teleop/robot data - close to human-level dexterity and efficiency - multi-robot collab

2:19
Vector Wang avatar
Vector Wang@VectorWang2·Sep 10

Presenting RoboTok: making human skills on the web searchable for robots. Given one demo, it finds similar actions using body-relative 3D hand trajectories across viewpoints and scenes for better dexterous policies. Project: rice-robotpi-lab.github.io/R… Code: github.com/Rice-RobotPI-Lab/… Data and models: huggingface.co/Rice-RobotPI-… Thanks @NVIDIAAI for supporting this work through the #NVIDIAGrant!

2:06
Yunfei Xie avatar
⟳ Vector Wang retweeted
Yunfei Xie@xiynfi1520580·Sep 4

🤖 Introducing RoboTok, the “TikTok for robots.” Just as TikTok recommends videos to people, RoboTok recommends relevant human demonstrations for robot learning. Robot learning needs broad and diverse demonstrations, but collecting robot data is expensive. RoboTok is an internet-scale data engine that uses web video as a scalable and continuously growing source of demonstrations for dexterous manipulation learning. Given one human demonstration video as a query, RoboTok retrieves other web videos with similar underlying manipulation motions. Rather than matching videos by labels or visual appearance, RoboTok compares how the hands move over time. 💡 The key idea is to represent each video with canonicalized 3D hand trajectories. Each trajectory is expressed in an estimated actor-centered reference frame, so the movement is described relative to the person rather than the camera. This makes similar manipulation behaviors easier to compare across different viewpoints and scenes, even when the actor is partly occluded. In our experiments, RoboTok retrieved more manipulation-relevant demonstrations than existing robot-data retrieval methods. When those videos were used to guide robot training, the simulated robots completed manipulation tasks more successfully. I’m sincerely grateful to Howard Qian and Kaiyu Hang for leading this project. I also want to thank Yiting Chen, Kejia Ren, Podshara Chanrungmaneekul, Gaotian Wang, Bowen Wen @bowenwen_me, and Chen Wei @_Chen_Wei_ for their guidance and collaboration. Project site: rice-robotpi-lab.github.io/R… Paper: arxiv.org/abs/2609.03199 Code: github.com/Rice-RobotPI-Lab/… Data and models: huggingface.co/Rice-RobotPI-…

2:06
Vector Wang avatar
Vector Wang@VectorWang2·Sep 4

In the “TikTok” for manipulation data, the searching algorithm should not only be based on the task text description, but also the hand motion itself

Robot learning has a data problem: the internet contains billions of human manipulation videos, but most robot datasets cover only a tiny fraction of real-world behavior. RoboTok turns those videos into a searchable source of dexterous manipulation demonstrations. Give it one human demonstration, and it retrieves other videos with similar hand movements.

2:06
Vector Wang avatar
Vector Wang@VectorWang2·Aug 25

Come and show your works and demos in agentic robotics! See you soon at Austin!

🚨 Call for live demo / paper at CoRL 2026 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽! No paper required for demo track. Due Sep 27. 🔮 The real magical power of agent is live interactive demo with the audience, which is why we provide all-out support: - Robot, compute, and API are ready for you in the conference room - Custom robot / sim demo also welcomed - Just submit a video proof - friendly to industrial participants agentic-robotics-workshop.gi… Paper submission also welcomed! We also have an amazing speaker lineup from CMU, UC Berkeley, DeepMind, NVIDIA, and Tencent.

Post attachment
Elie Aljalbout ✈️ CoRL avatar
⟳ Vector Wang retweeted
Elie Aljalbout ✈️ CoRL@EliJalbout·Aug 5

We're hiring! The Seattle Robotics Lab (SRL) at NVIDIA is hiring a research scientist to work on robot foundation models. The focus will be on investigating the science behind building VLAs, WAMs, and world models for robotics, and leveraging the findings to propose the next generation of models and training paradigms. We're seeking a world-class researcher (PhD grad) or senior researcher (3+ years of post-PhD experience) with expertise in training generalist policies. The researcher should aim to question conventional wisdom, push beyond the status quo, and dive into the foundations of general-purpose robot intelligence. NVIDIA SRL provides a rare environment to conduct open research on fundamental and applied robotics, with the freedom to publish, collaborate broadly, and tackle big scientific questions at scale. If this sounds like a strong fit, please reach out to us and apply here! nvidia.eightfold.ai/careers/… nvidia.eightfold.ai/careers/…